Importing all the libraries¶

In [1]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.neighbors import KNeighborsRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor,AdaBoostRegressor,GradientBoostingRegressor, ExtraTreesRegressor
from sklearn.svm import SVR
from sklearn.linear_model import LinearRegression,Lasso, Ridge
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error
from catboost import CatBoostRegressor
from xgboost import XGBRegressor
from sklearn.svm import SVR, NuSVR
from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.metrics import make_scorer
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LeakyReLU


from warnings import filterwarnings
filterwarnings("ignore")

Importing the dataset¶

In [2]:
df = pd.read_csv("/kaggle/input/biomass-cleaned-dataset/biomass data.csv")

Exploratory Data Analysis¶

In [3]:
df.describe()
Out[3]:
sl no MC VM FC Ash C H O N S oC ER S/B CO CO2 H2 CH4 Gas (m3/kg) Tar (g/m^3)
count 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 414.000000 414.000000 414.000000 414.000000 268.000000 124.000000
mean 225.500000 8.527356 71.909667 15.288511 4.289467 49.434578 6.090178 43.443067 0.699333 0.334000 802.198000 0.175600 0.612667 30.953309 28.829203 32.212874 8.004638 1.569813 13.713065
std 130.048068 3.672753 7.987731 4.021544 5.753450 3.342011 1.229714 3.929314 0.935660 0.719897 87.353518 0.140539 0.747409 9.045725 10.765455 13.362743 3.340170 0.657992 18.370045
min 1.000000 4.560000 52.560000 3.120000 0.010000 43.300000 0.080000 31.010000 0.010000 0.000000 599.000000 0.000000 0.000000 7.370000 5.000000 6.360000 0.430000 0.260000 0.540000
25% 113.250000 6.110000 66.900000 12.570000 0.500000 46.920000 5.620000 41.340000 0.160000 0.030000 750.000000 0.000000 0.000000 23.865000 20.072500 22.610000 5.715000 1.100000 3.475000
50% 225.500000 8.000000 75.180000 15.610000 1.510000 50.200000 6.210000 42.990000 0.530000 0.110000 800.000000 0.210000 0.390000 31.475000 28.255000 30.065000 7.930000 1.520000 7.650000
75% 337.750000 9.800000 77.710000 16.940000 5.330000 50.820000 6.780000 46.420000 0.900000 0.400000 850.000000 0.280000 1.050000 38.052500 36.530000 40.875000 10.000000 2.100000 15.125000
max 450.000000 27.000000 86.740000 26.450000 19.520000 58.340000 8.660000 51.830000 6.550000 4.200000 1108.000000 0.500000 4.700000 50.560000 59.040000 65.660000 22.000000 3.300000 91.430000
In [4]:
df.head()
Out[4]:
sl no Biomass species MC VM FC Ash C H O N S oC ER S/B CO CO2 H2 CH4 Gas (m3/kg) Tar (g/m^3)
0 1.0 Corn Stover 6.34 67.25 15.64 10.68 52.26 6.03 40.67 0.97 0.07 650.0 0.0 1.0 27.26 26.16 29.69 16.89 NaN NaN
1 2.0 Vermont Wood 4.56 81.51 13.55 0.38 54.51 6.21 39.15 0.11 0.03 650.0 0.0 1.0 25.66 26.20 31.22 16.92 NaN NaN
2 3.0 Wheat Straw 5.18 67.89 14.89 12.04 58.34 6.40 34.79 0.36 0.11 650.0 0.0 1.0 30.15 24.12 27.85 17.87 NaN NaN
3 4.0 Switchgrass 8.38 69.63 14.66 7.33 50.61 5.82 42.77 0.71 0.10 650.0 0.0 1.0 35.66 20.84 25.24 18.26 NaN NaN
4 5.0 Rice Husk 9.84 65.07 16.13 8.96 45.09 5.93 46.87 0.59 1.52 850.0 0.0 0.3 37.28 15.11 37.78 9.82 0.4 NaN
In [5]:
df.columns
Out[5]:
Index(['sl no', 'Biomass species', 'MC', 'VM', 'FC', 'Ash', 'C', 'H', 'O', 'N',
       'S', 'oC', 'ER', 'S/B', 'CO', 'CO2', 'H2', 'CH4', 'Gas (m3/kg)',
       'Tar (g/m^3)'],
      dtype='object')
In [6]:
df.drop(columns = ['sl no'], inplace = True)
In [7]:
df.columns
Out[7]:
Index(['Biomass species', 'MC', 'VM', 'FC', 'Ash', 'C', 'H', 'O', 'N', 'S',
       'oC', 'ER', 'S/B', 'CO', 'CO2', 'H2', 'CH4', 'Gas (m3/kg)',
       'Tar (g/m^3)'],
      dtype='object')
In [8]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 453 entries, 0 to 452
Data columns (total 19 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Biomass species  450 non-null    object 
 1   MC               450 non-null    float64
 2   VM               450 non-null    float64
 3   FC               450 non-null    float64
 4   Ash              450 non-null    float64
 5   C                450 non-null    float64
 6   H                450 non-null    float64
 7   O                450 non-null    float64
 8   N                450 non-null    float64
 9   S                450 non-null    float64
 10  oC               450 non-null    float64
 11  ER               450 non-null    float64
 12  S/B              450 non-null    float64
 13  CO               414 non-null    float64
 14  CO2              414 non-null    float64
 15  H2               414 non-null    float64
 16  CH4              414 non-null    float64
 17  Gas (m3/kg)      268 non-null    float64
 18  Tar (g/m^3)      124 non-null    float64
dtypes: float64(18), object(1)
memory usage: 67.4+ KB
In [9]:
df['Biomass species'].value_counts()
Out[9]:
Biomass species
Pine Sawdust                               70
Rice Husk                                  32
Wood Residue                               25
Sawdust                                    23
Pine wood                                  19
Empty Fruit Bunch                          19
Wood Pellets                               17
Rice husk                                  17
Rice Straw                                 15
Pine Chips                                 15
Artificial waste (including wood chips)    14
Groundnut Shell                            13
Sugarcane Bagasse                          13
Corn Straw                                 12
Ecualyptus Sawdust                         10
Peat                                        9
Palm Oil Wastes                             9
Legume Straw                                9
Wood Chips                                  9
Coconut Shell                               8
Rubber Woodchip                             7
Pine waste                                  7
Olive Stone                                 7
C. cardunculus L                            5
Olive Tree Cuttings                         5
Rubber Wood Chip                            5
Miscanthus Pellet                           5
Olive kernels                               5
Poultry litter                              4
Sunflower                                   4
Orujillo                                    4
Crushed Peat Pellets                        4
Willow                                      4
Holm-oak                                    4
Woody biomass                               4
Eucalyptus                                  4
Wood Pellet                                 3
Spruce Wood Pellets                         3
Vermont Wood                                1
Corn Stover                                 1
Switchgrass                                 1
Wheat Straw                                 1
Artificial waste(including wood chips)      1
Dried Grains                                1
Woody Biomass                               1
Bark Pellet                                 1
Name: count, dtype: int64

Pair plot¶

In [10]:
# sns.pairplot(df, hue='Biomass species')
# plt.show()
In [11]:
categorical_col = ['Biomass species']
numerical_col = df.select_dtypes(include='float').columns.tolist()
target_col = numerical_col[12:18]
numerical_col = numerical_col[:12]
In [12]:
print(numerical_col)
print(target_col)
print(categorical_col)

['MC', 'VM', 'FC', 'Ash', 'C', 'H', 'O', 'N', 'S', 'oC', 'ER', 'S/B']
['CO', 'CO2', 'H2', 'CH4', 'Gas (m3/kg)', 'Tar (g/m^3)']
['Biomass species']

Histplot¶

In [13]:
for col in numerical_col:
    plt.figure(figsize=(6, 4))
    sns.kdeplot(data=df[col], fill=True)
    plt.title(f'KDE of {col}')
    plt.xlabel(col)
    plt.ylabel('Density')
    plt.tight_layout()
    plt.show()
In [14]:
for col in numerical_col:
    plt.figure(figsize=(6, 4))
    sns.boxplot(x=df[col])
    plt.title(f'Boxplot of {col}')
    plt.tight_layout()
    plt.show()

There are a few outliers present in the dataset

In [15]:
plt.figure(figsize= (20,20))
corr = df.select_dtypes(include='number').corr()
sns.heatmap(corr, annot=True, cmap='coolwarm')
plt.title('Correlation between Features')
plt.show()

Ash and VM has 0.78 neg correlation and O and C have very high negative correlation

In [16]:
plt.figure(figsize=(80,16))
sns.countplot(x = 'Biomass species', data = df);

There is an uneven distribution in the count of categorical values

In [17]:
for tar_col in target_col:
    for num_col in numerical_col:
        plt.figure(figsize=(6,4))
        sns.scatterplot(x = df[num_col], y = df[tar_col])
        plt.show()

Preprocessing¶

In [18]:
df = df.iloc[:-3]
df.tail()
Out[18]:
Biomass species MC VM FC Ash C H O N S oC ER S/B CO CO2 H2 CH4 Gas (m3/kg) Tar (g/m^3)
445 Wood Pellets 5.92 76.13 17.29 0.66 49.87 5.81 42.26 2.0 0.06 813.0 0.30 0.0 NaN NaN NaN NaN 1.02 16.9
446 Orujillo 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 770.0 0.16 0.0 NaN NaN NaN NaN 1.21 16.1
447 Orujillo 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 830.0 0.23 0.0 NaN NaN NaN NaN 1.37 12.3
448 Orujillo 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 835.0 0.24 0.0 NaN NaN NaN NaN 1.41 11.6
449 Orujillo 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 870.0 0.31 0.0 NaN NaN NaN NaN 1.47 9.9
In [19]:
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
df['Biomass species'] = le.fit_transform(df['Biomass species'])
In [20]:
df['Biomass species'].unique().shape
Out[20]:
(46,)
In [21]:
df.tail()
Out[21]:
Biomass species MC VM FC Ash C H O N S oC ER S/B CO CO2 H2 CH4 Gas (m3/kg) Tar (g/m^3)
445 42 5.92 76.13 17.29 0.66 49.87 5.81 42.26 2.0 0.06 813.0 0.30 0.0 NaN NaN NaN NaN 1.02 16.9
446 19 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 770.0 0.16 0.0 NaN NaN NaN NaN 1.21 16.1
447 19 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 830.0 0.23 0.0 NaN NaN NaN NaN 1.37 12.3
448 19 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 835.0 0.24 0.0 NaN NaN NaN NaN 1.41 11.6
449 19 8.00 59.83 19.12 13.05 53.32 6.10 38.31 2.1 0.17 870.0 0.31 0.0 NaN NaN NaN NaN 1.47 9.9
In [22]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 450 entries, 0 to 449
Data columns (total 19 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Biomass species  450 non-null    int64  
 1   MC               450 non-null    float64
 2   VM               450 non-null    float64
 3   FC               450 non-null    float64
 4   Ash              450 non-null    float64
 5   C                450 non-null    float64
 6   H                450 non-null    float64
 7   O                450 non-null    float64
 8   N                450 non-null    float64
 9   S                450 non-null    float64
 10  oC               450 non-null    float64
 11  ER               450 non-null    float64
 12  S/B              450 non-null    float64
 13  CO               414 non-null    float64
 14  CO2              414 non-null    float64
 15  H2               414 non-null    float64
 16  CH4              414 non-null    float64
 17  Gas (m3/kg)      268 non-null    float64
 18  Tar (g/m^3)      124 non-null    float64
dtypes: float64(18), int64(1)
memory usage: 66.9 KB
In [23]:
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
data = df[['Ash', 'VM']]

# Scale the data
scaler = StandardScaler()
data_scaled = scaler.fit_transform(data)
# Step 2: Perform PCA
# Since we have two features, we can set n_components to 2 (or less, if you want to reduce dimensions further)
pca = PCA(n_components=2)
principal_components = pca.fit_transform(data_scaled)

# Step 3: Create a DataFrame with the principal components
pc_df = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])

print("Principal Components:")
print(pc_df)

print("\nExplained Variance Ratio:")
print(pca.explained_variance_ratio_)

Principal Components:
          PC1       PC2
0    1.199231 -0.373327
1   -1.331820 -0.369793
2    1.309845 -0.597378
3    0.576132 -0.172071
4    1.180803  0.031496
..        ...       ...
445 -0.820580  0.072546
446  2.148411 -0.007348
447  2.148411 -0.007348
448  2.148411 -0.007348
449  2.148411 -0.007348

[450 rows x 2 columns]

Explained Variance Ratio:
[0.88808869 0.11191131]

Between Ash and VM the PC1 has captured 88% variance as it is not more than 90 so I am not replacing them in the original dataframe

In [24]:
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
data = df[['O', 'C']]

# Scale the data
scaler = StandardScaler()
data_scaled = scaler.fit_transform(data)
# Step 2: Perform PCA
# Since we have two features, we can set n_components to 2 (or less, if you want to reduce dimensions further)
pca = PCA(n_components=2)
principal_components = pca.fit_transform(data_scaled)

# Step 3: Create a DataFrame with the principal components
pc_df = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])

print("Principal Components:")
print(pc_df)

print("\nExplained Variance Ratio:")
print(pca.explained_variance_ratio_)

Principal Components:
          PC1       PC2
0    1.098059  0.098884
1    1.848486  0.301633
2    3.445228  0.327406
3    0.370232  0.127716
4   -1.537640 -0.302868
..        ...       ...
445  0.305368 -0.120908
446  1.747756 -0.101761
447  1.747756 -0.101761
448  1.747756 -0.101761
449  1.747756 -0.101761

[450 rows x 2 columns]

Explained Variance Ratio:
[0.95675092 0.04324908]
In [25]:
# Optionally, if you're sure, drop the original 'O' and 'C' columns
df_reduced = df.drop(['O', 'C'], axis=1)
df_reduced['PC1'] = principal_components[:, 0]

replaced the C and O column with PC1 and the variance captured by PC1 is more than 95%

In [26]:
df_reduced.head()
Out[26]:
Biomass species MC VM FC Ash H N S oC ER S/B CO CO2 H2 CH4 Gas (m3/kg) Tar (g/m^3) PC1
0 5 6.34 67.25 15.64 10.68 6.03 0.97 0.07 650.0 0.0 1.0 27.26 26.16 29.69 16.89 NaN NaN 1.098059
1 37 4.56 81.51 13.55 0.38 6.21 0.11 0.03 650.0 0.0 1.0 25.66 26.20 31.22 16.92 NaN NaN 1.848486
2 38 5.18 67.89 14.89 12.04 6.40 0.36 0.11 650.0 0.0 1.0 30.15 24.12 27.85 17.87 NaN NaN 3.445228
3 36 8.38 69.63 14.66 7.33 5.82 0.71 0.10 650.0 0.0 1.0 35.66 20.84 25.24 18.26 NaN NaN 0.370232
4 27 9.84 65.07 16.13 8.96 5.93 0.59 1.52 850.0 0.0 0.3 37.28 15.11 37.78 9.82 0.4 NaN -1.537640
In [27]:
df_reduced.describe()
Out[27]:
Biomass species MC VM FC Ash H N S oC ER S/B CO CO2 H2 CH4 Gas (m3/kg) Tar (g/m^3) PC1
count 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 450.000000 414.000000 414.000000 414.000000 414.000000 268.000000 124.000000 4.500000e+02
mean 23.642222 8.527356 71.909667 15.288511 4.289467 6.090178 0.699333 0.334000 802.198000 0.175600 0.612667 30.953309 28.829203 32.212874 8.004638 1.569813 13.713065 -3.157968e-17
std 11.366676 3.672753 7.987731 4.021544 5.753450 1.229714 0.935660 0.719897 87.353518 0.140539 0.747409 9.045725 10.765455 13.362743 3.340170 0.657992 18.370045 1.384833e+00
min 0.000000 4.560000 52.560000 3.120000 0.010000 0.080000 0.010000 0.000000 599.000000 0.000000 0.000000 7.370000 5.000000 6.360000 0.430000 0.260000 0.540000 -2.789190e+00
25% 16.000000 6.110000 66.900000 12.570000 0.500000 5.620000 0.160000 0.030000 750.000000 0.000000 0.000000 23.865000 20.072500 22.610000 5.715000 1.100000 3.475000 -9.219701e-01
50% 23.000000 8.000000 75.180000 15.610000 1.510000 6.210000 0.530000 0.110000 800.000000 0.210000 0.390000 31.475000 28.255000 30.065000 7.930000 1.520000 7.650000 2.862740e-01
75% 31.000000 9.800000 77.710000 16.940000 5.330000 6.780000 0.900000 0.400000 850.000000 0.280000 1.050000 38.052500 36.530000 40.875000 10.000000 2.100000 15.125000 6.723379e-01
max 45.000000 27.000000 86.740000 26.450000 19.520000 8.660000 6.550000 4.200000 1108.000000 0.500000 4.700000 50.560000 59.040000 65.660000 22.000000 3.300000 91.430000 3.445228e+00

Train test split¶

In [28]:
df['Biomass species'].value_counts().sort_index()
Out[28]:
Biomass species
0     14
1      1
2      1
3      5
4      8
5      1
6     12
7      4
8      1
9     10
10    19
11     4
12    13
13     4
14     9
15     5
16     7
17     5
18     5
19     4
20     9
21     9
22    15
23    70
24     7
25    19
26     4
27    32
28    15
29    17
30     5
31     7
32    23
33     3
34    13
35     4
36     1
37     1
38     1
39     4
40     9
41     3
42    17
43    25
44     1
45     4
Name: count, dtype: int64
In [29]:
null_counts = df.groupby('Biomass species')[['CO', 'CO2', 'H2', 'CH4']].apply(lambda x: x.isnull().sum())
print(null_counts)

                 CO  CO2  H2  CH4
Biomass species                  
0                 0    0   0    0
1                 0    0   0    0
2                 1    1   1    1
3                 0    0   0    0
4                 0    0   0    0
5                 0    0   0    0
6                 0    0   0    0
7                 4    4   4    4
8                 0    0   0    0
9                 0    0   0    0
10                0    0   0    0
11                0    0   0    0
12                0    0   0    0
13                0    0   0    0
14                0    0   0    0
15                0    0   0    0
16                0    0   0    0
17                0    0   0    0
18                0    0   0    0
19                4    4   4    4
20                0    0   0    0
21                0    0   0    0
22                0    0   0    0
23                0    0   0    0
24                0    0   0    0
25                0    0   0    0
26                0    0   0    0
27                0    0   0    0
28                0    0   0    0
29                0    0   0    0
30                0    0   0    0
31                0    0   0    0
32                0    0   0    0
33                0    0   0    0
34                0    0   0    0
35                0    0   0    0
36                0    0   0    0
37                0    0   0    0
38                0    0   0    0
39                0    0   0    0
40                0    0   0    0
41                0    0   0    0
42                8    8   8    8
43               18   18  18   18
44                1    1   1    1
45                0    0   0    0
In [30]:
strings_to_remove = ['Gas (m3/kg)', 'Tar (g/m^3)']
target_col = [item for item in target_col if item not in strings_to_remove]
In [31]:
df.drop(['Gas (m3/kg)', 'Tar (g/m^3)'], axis =1, inplace = True)
In [32]:
x_test = df[df['CO'].isna()]

# Remove those rows from the original DataFrame
df_up = df[~df['CO'].isna()]
In [33]:
x_test.info()

<class 'pandas.core.frame.DataFrame'>
Index: 36 entries, 192 to 449
Data columns (total 17 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Biomass species  36 non-null     int64  
 1   MC               36 non-null     float64
 2   VM               36 non-null     float64
 3   FC               36 non-null     float64
 4   Ash              36 non-null     float64
 5   C                36 non-null     float64
 6   H                36 non-null     float64
 7   O                36 non-null     float64
 8   N                36 non-null     float64
 9   S                36 non-null     float64
 10  oC               36 non-null     float64
 11  ER               36 non-null     float64
 12  S/B              36 non-null     float64
 13  CO               0 non-null      float64
 14  CO2              0 non-null      float64
 15  H2               0 non-null      float64
 16  CH4              0 non-null      float64
dtypes: float64(16), int64(1)
memory usage: 5.1 KB
In [34]:
df_up.info()

<class 'pandas.core.frame.DataFrame'>
Index: 414 entries, 0 to 431
Data columns (total 17 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Biomass species  414 non-null    int64  
 1   MC               414 non-null    float64
 2   VM               414 non-null    float64
 3   FC               414 non-null    float64
 4   Ash              414 non-null    float64
 5   C                414 non-null    float64
 6   H                414 non-null    float64
 7   O                414 non-null    float64
 8   N                414 non-null    float64
 9   S                414 non-null    float64
 10  oC               414 non-null    float64
 11  ER               414 non-null    float64
 12  S/B              414 non-null    float64
 13  CO               414 non-null    float64
 14  CO2              414 non-null    float64
 15  H2               414 non-null    float64
 16  CH4              414 non-null    float64
dtypes: float64(16), int64(1)
memory usage: 58.2 KB
In [35]:
category_counts = df_up['Biomass species'].value_counts()

# Separate rare (count == 1) and common (count >= 2) categories
rare_categories = category_counts[category_counts <= 2].index
common_categories = category_counts[category_counts > 2].index

# 1. Put rare category rows directly into x_train and y_train
df_rare = df_up[df_up['Biomass species'].isin(rare_categories)]
x_train_rare = df_rare.drop(columns=target_col)
y_train_rare = df_rare[target_col]

# 2. Use stratified split on the rest (common categories)
df_common = df_up[df_up['Biomass species'].isin(common_categories)]

X_common = df_common.drop(columns=target_col)
y_common = df_common[target_col]

x_train_common, x_val, y_train_common, y_val = train_test_split(
    X_common, y_common, test_size=0.3, stratify=df_common['Biomass species'], random_state=42
)

# 3. Combine both parts into final x_train and y_train
x_train = pd.concat([x_train_common, x_train_rare]).reset_index(drop=True)
y_train = pd.concat([y_train_common, y_train_rare]).reset_index(drop=True)
In [36]:
print(x_train.shape, y_train.shape, x_val.shape, y_val.shape)

(291, 13) (291, 4) (123, 13) (123, 4)
In [37]:
sc = StandardScaler()
X_train_scaled = sc.fit_transform(x_train)
X_val_scaled = sc.transform(x_val)

Models¶

Linear Regression¶

In [38]:
y_val
Out[38]:
CO CO2 H2 CH4
373 32.08 43.56 17.80 6.56
166 16.16 25.51 52.13 6.20
277 29.40 32.45 32.58 5.57
61 16.24 27.77 51.93 4.06
230 19.80 10.89 54.46 14.85
... ... ... ... ...
351 16.00 55.00 20.00 9.00
219 39.57 20.56 32.97 6.90
84 23.12 18.05 55.17 3.65
428 33.70 35.20 23.40 7.70
22 39.57 18.76 33.76 7.91

123 rows × 4 columns

In [39]:
lr = LinearRegression()
lr.fit(X_train_scaled, y_train)
y_pred_lr = lr.predict(X_val_scaled)
r2 = r2_score(y_val, y_pred_lr)
print(r2)

0.4642857004670947

SVR¶

In [40]:
from sklearn.multioutput import MultiOutputRegressor as MOR
In [41]:
svr = MOR(SVR(kernel='rbf', C = 100, gamma=0.1, epsilon =0.1))
svr.fit(X_train_scaled, y_train)
y_pred_svr = svr.predict(X_val_scaled)
r2 = r2_score(y_val, y_pred_svr)
r2
Out[41]:
0.8597656722127263

Random Forest¶

In [42]:
rf = MOR(RandomForestRegressor(n_estimators = 100, random_state = 0))
rf.fit(X_train_scaled, y_train)
y_pred_rf = rf.predict(X_val_scaled)
r2 = r2_score(y_val, y_pred_rf)
r2
Out[42]:
0.8593649636831314

XG Boost¶

In [43]:
xgbr = MOR(XGBRegressor())
xgbr.fit(X_train_scaled, y_train)
y_pred_xgbr = xgbr.predict(X_val_scaled)
r2 = r2_score(y_val, y_pred_xgbr)
r2
Out[43]:
0.8437070181957863

CatBoost¶

In [44]:
catr = MOR(CatBoostRegressor(verbose = 0, iterations = 100))
catr.fit(X_train_scaled, y_train)
y_pred_catr = catr.predict(X_val_scaled)
r2 = r2_score(y_val, y_pred_catr)
r2
Out[44]:
0.8757567617515191

Prediction for CO¶

In [45]:
ANN_model = Sequential([
    Dense(32, input_dim=13),                  # No activation here
    LeakyReLU(alpha=0.1),                    # LeakyReLU activation
    Dense(32, activation='tanh'),            # Tanh for richer non-linearity
    Dense(16, activation='relu'),            # ReLU for simplicity
    Dense(1, activation='linear')            # Linear for regression output
])

# Compile the model
ANN_model.compile(optimizer='adam',
              loss='mean_squared_error',
              metrics=['mae'])


# Train the model
ANN_model.fit(X_train_scaled, y_train.CO, epochs=500, verbose=1)

# Evaluate the model
loss, mae = ANN_model.evaluate(X_train_scaled, y_train.CO, verbose=0)
print(f"\nModel evaluation:\nLoss (MSE): {loss:.2f}, MAE: {mae:.2f}")

Epoch 1/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - loss: 1049.5668 - mae: 31.1556
Epoch 2/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 990.8082 - mae: 30.2402  
Epoch 3/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 997.6783 - mae: 30.2056 
Epoch 4/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 946.1098 - mae: 29.4611 
Epoch 5/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 875.7856 - mae: 28.1450 
Epoch 6/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 812.5873 - mae: 27.0314 
Epoch 7/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 784.5808 - mae: 26.4351 
Epoch 8/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 629.8642 - mae: 23.3735 
Epoch 9/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 604.7215 - mae: 22.6841 
Epoch 10/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 474.7732 - mae: 19.9527 
Epoch 11/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 386.4395 - mae: 17.4614 
Epoch 12/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 305.8181 - mae: 15.1905 
Epoch 13/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 233.2466 - mae: 12.9242 
Epoch 14/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 193.7127 - mae: 11.7246 
Epoch 15/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 150.3445 - mae: 10.4185 
Epoch 16/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 121.2733 - mae: 9.2584 
Epoch 17/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 106.8774 - mae: 8.6945 
Epoch 18/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 90.4864 - mae: 8.0807 
Epoch 19/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 87.8201 - mae: 7.8085  
Epoch 20/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 74.9877 - mae: 7.2468 
Epoch 21/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 76.6438 - mae: 7.2888 
Epoch 22/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 73.5152 - mae: 7.1648 
Epoch 23/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 71.0906 - mae: 6.9862 
Epoch 24/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 73.8597 - mae: 7.1195 
Epoch 25/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 64.4932 - mae: 6.5665 
Epoch 26/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 68.5440 - mae: 6.7592 
Epoch 27/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 68.2444 - mae: 6.7819 
Epoch 28/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 54.3098 - mae: 5.9240 
Epoch 29/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 66.5484 - mae: 6.6636 
Epoch 30/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 59.9352 - mae: 6.1679 
Epoch 31/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 58.0923 - mae: 6.1950 
Epoch 32/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 59.9825 - mae: 6.2434 
Epoch 33/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 64.6556 - mae: 6.3879 
Epoch 34/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 59.0059 - mae: 6.1226 
Epoch 35/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 55.5718 - mae: 5.8198 
Epoch 36/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 57.1887 - mae: 5.9417 
Epoch 37/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 55.4530 - mae: 6.0229 
Epoch 38/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 57.8251 - mae: 6.1345 
Epoch 39/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 57.2762 - mae: 6.0623 
Epoch 40/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 58.1037 - mae: 6.1595 
Epoch 41/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 57.7948 - mae: 6.0099 
Epoch 42/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 59.4623 - mae: 6.0884 
Epoch 43/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 58.5125 - mae: 6.0615 
Epoch 44/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 60.8963 - mae: 6.2569 
Epoch 45/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 55.7482 - mae: 6.0097 
Epoch 46/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 50.2650 - mae: 5.6216 
Epoch 47/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 52.2891 - mae: 5.7414 
Epoch 48/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 56.5041 - mae: 5.9530 
Epoch 49/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 50.2919 - mae: 5.5421 
Epoch 50/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 49.1641 - mae: 5.5442 
Epoch 51/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 45.6205 - mae: 5.2689 
Epoch 52/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 48.7371 - mae: 5.5629 
Epoch 53/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 48.2250 - mae: 5.5235 
Epoch 54/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 50.6296 - mae: 5.5812 
Epoch 55/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 42.4191 - mae: 5.1308 
Epoch 56/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 43.2791 - mae: 5.1268 
Epoch 57/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 46.3677 - mae: 5.4436 
Epoch 58/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 47.5146 - mae: 5.3818 
Epoch 59/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 45.9024 - mae: 5.3736 
Epoch 60/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 45.0861 - mae: 5.2716 
Epoch 61/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 43.4712 - mae: 5.1133 
Epoch 62/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 39.0592 - mae: 4.8002 
Epoch 63/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 43.6977 - mae: 5.2156 
Epoch 64/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 40.8246 - mae: 4.9551 
Epoch 65/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 39.5400 - mae: 4.8716 
Epoch 66/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 40.3137 - mae: 4.9308 
Epoch 67/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 40.6637 - mae: 4.9948 
Epoch 68/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 46.0055 - mae: 5.3520 
Epoch 69/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.6940 - mae: 4.8441 
Epoch 70/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 38.4222 - mae: 4.9042 
Epoch 71/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.4353 - mae: 4.7259 
Epoch 72/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 35.1792 - mae: 4.6057 
Epoch 73/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 39.6806 - mae: 4.7793 
Epoch 74/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 38.8105 - mae: 4.8041 
Epoch 75/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 35.2362 - mae: 4.5829 
Epoch 76/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 35.0303 - mae: 4.5737 
Epoch 77/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 36.8052 - mae: 4.7044 
Epoch 78/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.3093 - mae: 4.4273 
Epoch 79/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 31.5110 - mae: 4.3561 
Epoch 80/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.6505 - mae: 4.7359 
Epoch 81/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.3553 - mae: 4.5196 
Epoch 82/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 31.5304 - mae: 4.4196 
Epoch 83/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 28.1999 - mae: 4.1188 
Epoch 84/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 35.5382 - mae: 4.6962 
Epoch 85/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.0853 - mae: 4.3008 
Epoch 86/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 29.7146 - mae: 4.2753 
Epoch 87/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 28.1309 - mae: 4.0398 
Epoch 88/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 31.4374 - mae: 4.2591 
Epoch 89/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 29.4820 - mae: 4.1664 
Epoch 90/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 26.1225 - mae: 3.8892 
Epoch 91/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.2259 - mae: 3.9730 
Epoch 92/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.5490 - mae: 3.7907 
Epoch 93/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.6922 - mae: 4.0293 
Epoch 94/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.6301 - mae: 3.9065 
Epoch 95/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 26.7401 - mae: 3.9771 
Epoch 96/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.9769 - mae: 3.9282 
Epoch 97/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.4226 - mae: 3.8476 
Epoch 98/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.9323 - mae: 3.5304 
Epoch 99/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.3618 - mae: 3.9609 
Epoch 100/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.9963 - mae: 3.7854 
Epoch 101/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.6444 - mae: 3.7258 
Epoch 102/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.9058 - mae: 3.5608 
Epoch 103/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.8688 - mae: 3.5154 
Epoch 104/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.2191 - mae: 3.9576 
Epoch 105/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 28.1785 - mae: 3.8518 
Epoch 106/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.8801 - mae: 3.5336 
Epoch 107/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.9918 - mae: 3.6878 
Epoch 108/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.1551 - mae: 3.3090 
Epoch 109/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.7038 - mae: 3.5484 
Epoch 110/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.0876 - mae: 3.5077 
Epoch 111/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.2354 - mae: 3.6588 
Epoch 112/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 23.2939 - mae: 3.6849 
Epoch 113/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.6588 - mae: 3.4449 
Epoch 114/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.5717 - mae: 3.2436 
Epoch 115/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.8740 - mae: 3.3301 
Epoch 116/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.3815 - mae: 3.2860 
Epoch 117/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.1956 - mae: 3.4279 
Epoch 118/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.5456 - mae: 3.3085 
Epoch 119/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.0018 - mae: 3.3917 
Epoch 120/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.5345 - mae: 3.3947 
Epoch 121/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.6902 - mae: 3.1535 
Epoch 122/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.5010 - mae: 3.3366 
Epoch 123/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.4733 - mae: 3.2849 
Epoch 124/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.2049 - mae: 3.3962 
Epoch 125/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.7079 - mae: 3.0630
Epoch 126/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.8997 - mae: 3.0776
Epoch 127/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.1731 - mae: 2.9640 
Epoch 128/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.4506 - mae: 3.0995 
Epoch 129/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.2497 - mae: 3.0618 
Epoch 130/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.5432 - mae: 3.2767 
Epoch 131/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.9494 - mae: 3.1669 
Epoch 132/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.6547 - mae: 2.9171 
Epoch 133/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.7346 - mae: 3.0229 
Epoch 134/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.9137 - mae: 3.1245 
Epoch 135/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.5400 - mae: 3.3215 
Epoch 136/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.6561 - mae: 3.2664 
Epoch 137/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.0565 - mae: 3.0045 
Epoch 138/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.9809 - mae: 3.1107 
Epoch 139/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.3218 - mae: 3.1368 
Epoch 140/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.4129 - mae: 3.0626 
Epoch 141/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.9193 - mae: 3.0643 
Epoch 142/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.4840 - mae: 3.1768 
Epoch 143/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.2585 - mae: 3.0968 
Epoch 144/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.4544 - mae: 3.1746 
Epoch 145/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.4295 - mae: 3.0693 
Epoch 146/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.2559 - mae: 3.0132 
Epoch 147/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.7293 - mae: 2.9369 
Epoch 148/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.7350 - mae: 3.1985 
Epoch 149/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.5996 - mae: 3.1382 
Epoch 150/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.1582 - mae: 2.9745 
Epoch 151/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.4522 - mae: 2.7548
Epoch 152/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.2458 - mae: 2.8222 
Epoch 153/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.9354 - mae: 2.7755
Epoch 154/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.5355 - mae: 2.8087 
Epoch 155/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.6071 - mae: 2.6840
Epoch 156/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.7906 - mae: 2.8778 
Epoch 157/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.3160 - mae: 2.9861 
Epoch 158/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.5215 - mae: 2.6492
Epoch 159/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.7714 - mae: 2.8399
Epoch 160/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.2373 - mae: 2.9664
Epoch 161/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.0783 - mae: 2.9210 
Epoch 162/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.8620 - mae: 2.7460 
Epoch 163/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.6127 - mae: 2.8041 
Epoch 164/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.4618 - mae: 3.0441 
Epoch 165/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.2178 - mae: 2.7968 
Epoch 166/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.6241 - mae: 2.7654 
Epoch 167/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.4566 - mae: 2.5760
Epoch 168/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.8734 - mae: 2.8540 
Epoch 169/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.5075 - mae: 2.7120
Epoch 170/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - loss: 15.3931 - mae: 2.9061 
Epoch 171/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.7793 - mae: 2.6955 
Epoch 172/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.2681 - mae: 3.0696 
Epoch 173/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.7597 - mae: 2.6869 
Epoch 174/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.9697 - mae: 2.7104 
Epoch 175/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.3552 - mae: 2.8191 
Epoch 176/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.9031 - mae: 2.6247 
Epoch 177/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.6405 - mae: 2.7684 
Epoch 178/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.6220 - mae: 2.6508 
Epoch 179/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.4352 - mae: 2.6886 
Epoch 180/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.2032 - mae: 2.7976 
Epoch 181/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.1606 - mae: 2.5459
Epoch 182/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9826 - mae: 2.5154
Epoch 183/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.3524 - mae: 2.6852 
Epoch 184/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.3347 - mae: 2.7753 
Epoch 185/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.7059 - mae: 2.6754 
Epoch 186/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.7382 - mae: 2.9608 
Epoch 187/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.5628 - mae: 2.5736 
Epoch 188/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.1552 - mae: 2.3583
Epoch 189/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.8257 - mae: 2.5482 
Epoch 190/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.6458 - mae: 2.7296 
Epoch 191/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.6867 - mae: 2.6346 
Epoch 192/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.4644 - mae: 2.5646
Epoch 193/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8776 - mae: 2.4346
Epoch 194/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2379 - mae: 2.3383
Epoch 195/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.0399 - mae: 2.6771 
Epoch 196/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.1619 - mae: 2.7304 
Epoch 197/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.3813 - mae: 2.3802 
Epoch 198/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.4387 - mae: 2.3931
Epoch 199/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.2842 - mae: 2.4844
Epoch 200/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.9771 - mae: 2.2233 
Epoch 201/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.0037 - mae: 2.5338 
Epoch 202/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8396 - mae: 2.4309 
Epoch 203/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.0599 - mae: 2.5229 
Epoch 204/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.4750 - mae: 2.4653
Epoch 205/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.7590 - mae: 2.3797
Epoch 206/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.3996 - mae: 2.4322 
Epoch 207/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8096 - mae: 2.4042 
Epoch 208/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.2821 - mae: 2.6146 
Epoch 209/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8340 - mae: 2.3436
Epoch 210/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3319 - mae: 2.3593
Epoch 211/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.8783 - mae: 2.4590 
Epoch 212/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.6279 - mae: 2.4054 
Epoch 213/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2264 - mae: 2.3728 
Epoch 214/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9747 - mae: 2.3688 
Epoch 215/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.0189 - mae: 2.3585
Epoch 216/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6053 - mae: 2.2643 
Epoch 217/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.4804 - mae: 2.3079 
Epoch 218/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.6690 - mae: 2.3054 
Epoch 219/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.1003 - mae: 2.2849 
Epoch 220/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.7362 - mae: 2.3402 
Epoch 221/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7143 - mae: 2.2660 
Epoch 222/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.1649 - mae: 2.4281 
Epoch 223/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.4735 - mae: 2.3397 
Epoch 224/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.9349 - mae: 2.2391 
Epoch 225/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4857 - mae: 2.2126 
Epoch 226/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8658 - mae: 2.0347 
Epoch 227/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4893 - mae: 2.2164 
Epoch 228/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8990 - mae: 2.2382
Epoch 229/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6970 - mae: 2.0715 
Epoch 230/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.2404 - mae: 2.1493  
Epoch 231/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.6201 - mae: 2.2906 
Epoch 232/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.9761 - mae: 2.2215  
Epoch 233/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.1878 - mae: 2.1658
Epoch 234/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4778 - mae: 2.0545 
Epoch 235/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.0767 - mae: 2.1459
Epoch 236/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.6867 - mae: 2.3378 
Epoch 237/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.2053 - mae: 2.1621 
Epoch 238/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1747 - mae: 2.0918 
Epoch 239/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1489 - mae: 2.1063 
Epoch 240/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0646 - mae: 2.0497 
Epoch 241/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3317 - mae: 2.0287 
Epoch 242/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.1991 - mae: 2.3062 
Epoch 243/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7304 - mae: 2.0722  
Epoch 244/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0453 - mae: 1.9254 
Epoch 245/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8318 - mae: 1.9011 
Epoch 246/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.1199 - mae: 2.1026 
Epoch 247/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7387 - mae: 1.9115 
Epoch 248/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8999 - mae: 2.2430 
Epoch 249/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3109 - mae: 2.0055  
Epoch 250/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0610 - mae: 2.0578 
Epoch 251/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1976 - mae: 1.8884 
Epoch 252/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4156 - mae: 2.0387 
Epoch 253/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4914 - mae: 2.0217 
Epoch 254/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7322 - mae: 1.8796 
Epoch 255/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5904 - mae: 2.0052 
Epoch 256/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5525 - mae: 1.9877 
Epoch 257/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0220 - mae: 1.8718 
Epoch 258/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9664 - mae: 1.9287 
Epoch 259/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0896 - mae: 1.8996 
Epoch 260/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.7437 - mae: 1.9473 
Epoch 261/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8119 - mae: 2.0272 
Epoch 262/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.7180 - mae: 1.9775 
Epoch 263/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1631 - mae: 1.9030 
Epoch 264/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2763 - mae: 1.8540 
Epoch 265/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5749 - mae: 2.0115 
Epoch 266/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6657 - mae: 1.9886 
Epoch 267/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2563 - mae: 1.9849 
Epoch 268/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.2689 - mae: 2.0956  
Epoch 269/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9055 - mae: 1.9312  
Epoch 270/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6906 - mae: 1.9254 
Epoch 271/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8792 - mae: 1.8277 
Epoch 272/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5770 - mae: 1.7990 
Epoch 273/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0742 - mae: 1.8560 
Epoch 274/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0556 - mae: 1.9480 
Epoch 275/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7471 - mae: 1.8695 
Epoch 276/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5108 - mae: 1.8963 
Epoch 277/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5517 - mae: 1.9656  
Epoch 278/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2174 - mae: 1.7889 
Epoch 279/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1950 - mae: 1.9930  
Epoch 280/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9053 - mae: 1.8311 
Epoch 281/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5292 - mae: 1.8490 
Epoch 282/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4859 - mae: 1.8373 
Epoch 283/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6827 - mae: 2.1537  
Epoch 284/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8376 - mae: 1.9251 
Epoch 285/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7059 - mae: 2.1337  
Epoch 286/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2716 - mae: 1.9498  
Epoch 287/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1108 - mae: 2.0148 
Epoch 288/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7163 - mae: 1.8074 
Epoch 289/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0859 - mae: 2.0185 
Epoch 290/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2522 - mae: 2.0603 
Epoch 291/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9490 - mae: 1.9155 
Epoch 292/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4364 - mae: 1.8066 
Epoch 293/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4390 - mae: 1.7193 
Epoch 294/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5727 - mae: 1.9158 
Epoch 295/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8665 - mae: 1.8765 
Epoch 296/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5139 - mae: 1.8384 
Epoch 297/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7506 - mae: 1.8647 
Epoch 298/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9047 - mae: 1.8560  
Epoch 299/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6695 - mae: 1.8330 
Epoch 300/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7294 - mae: 1.8861 
Epoch 301/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6524 - mae: 1.6692 
Epoch 302/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1935 - mae: 1.7689 
Epoch 303/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4361 - mae: 1.7489 
Epoch 304/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0978 - mae: 1.7748 
Epoch 305/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4466 - mae: 1.7551 
Epoch 306/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2721 - mae: 1.8647  
Epoch 307/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9718 - mae: 1.8209 
Epoch 308/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7737 - mae: 1.8163 
Epoch 309/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4438 - mae: 1.6935 
Epoch 310/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5852 - mae: 1.7142 
Epoch 311/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7172 - mae: 1.8537  
Epoch 312/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2375 - mae: 1.8387 
Epoch 313/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7704 - mae: 1.7844 
Epoch 314/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4139 - mae: 1.9312 
Epoch 315/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1177 - mae: 1.7583 
Epoch 316/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8768 - mae: 1.8250 
Epoch 317/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2011 - mae: 1.6893 
Epoch 318/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7330 - mae: 1.7523 
Epoch 319/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6161 - mae: 1.7083 
Epoch 320/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0959 - mae: 1.7774 
Epoch 321/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6171 - mae: 1.8303  
Epoch 322/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8782 - mae: 1.6791 
Epoch 323/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7185 - mae: 1.7284 
Epoch 324/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9616 - mae: 1.8105 
Epoch 325/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4696 - mae: 1.7610 
Epoch 326/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8729 - mae: 1.6935 
Epoch 327/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1664 - mae: 1.7357 
Epoch 328/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6704 - mae: 1.7434 
Epoch 329/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3001 - mae: 1.8465 
Epoch 330/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8150 - mae: 1.9558 
Epoch 331/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2932 - mae: 1.7034 
Epoch 332/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2603 - mae: 1.7853  
Epoch 333/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5499 - mae: 1.6925 
Epoch 334/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - loss: 8.7210 - mae: 1.9415  
Epoch 335/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9925 - mae: 1.6494 
Epoch 336/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2069 - mae: 1.8744  
Epoch 337/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6790 - mae: 1.6815 
Epoch 338/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3123 - mae: 1.7971 
Epoch 339/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2852 - mae: 1.5632 
Epoch 340/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6461 - mae: 1.5981 
Epoch 341/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3203 - mae: 1.8182 
Epoch 342/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6392 - mae: 1.5989 
Epoch 343/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1923 - mae: 1.6714 
Epoch 344/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3421 - mae: 1.6650 
Epoch 345/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3046 - mae: 1.6799 
Epoch 346/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4212 - mae: 1.6465 
Epoch 347/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3622 - mae: 1.7005 
Epoch 348/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2949 - mae: 1.6205 
Epoch 349/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5990 - mae: 1.7172 
Epoch 350/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6478 - mae: 1.6617 
Epoch 351/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3573 - mae: 1.5831 
Epoch 352/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9858 - mae: 1.6435 
Epoch 353/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2687 - mae: 1.6461 
Epoch 354/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4730 - mae: 1.6991 
Epoch 355/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3315 - mae: 1.6084 
Epoch 356/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1780 - mae: 1.7549 
Epoch 357/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6276 - mae: 1.6008 
Epoch 358/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5822 - mae: 1.8368 
Epoch 359/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0110 - mae: 1.6983 
Epoch 360/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9595 - mae: 1.7618 
Epoch 361/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9245 - mae: 1.7864 
Epoch 362/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4756 - mae: 1.7513  
Epoch 363/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1827 - mae: 1.6452 
Epoch 364/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6116 - mae: 1.6548 
Epoch 365/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2185 - mae: 1.6619 
Epoch 366/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9426 - mae: 1.6803 
Epoch 367/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6353 - mae: 1.7295  
Epoch 368/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7616 - mae: 1.7835 
Epoch 369/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2137 - mae: 1.8449 
Epoch 370/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8921 - mae: 1.7813 
Epoch 371/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7580 - mae: 1.6400 
Epoch 372/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6586 - mae: 1.6028 
Epoch 373/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0027 - mae: 1.6208 
Epoch 374/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6781 - mae: 1.6282 
Epoch 375/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0329 - mae: 1.7236 
Epoch 376/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2406 - mae: 1.6525 
Epoch 377/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5417 - mae: 1.6719 
Epoch 378/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6530 - mae: 1.5459 
Epoch 379/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9457 - mae: 1.4770 
Epoch 380/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7267 - mae: 1.5772 
Epoch 381/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1328 - mae: 1.4794 
Epoch 382/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4178 - mae: 1.5186 
Epoch 383/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6627 - mae: 1.5477 
Epoch 384/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4242 - mae: 1.6301 
Epoch 385/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5287 - mae: 1.6035 
Epoch 386/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2384 - mae: 1.7793  
Epoch 387/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1052 - mae: 1.6029 
Epoch 388/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7544 - mae: 1.5868 
Epoch 389/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6347 - mae: 1.7125 
Epoch 390/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2089 - mae: 1.7078  
Epoch 391/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1454 - mae: 1.5662 
Epoch 392/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2118 - mae: 1.6337 
Epoch 393/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0658 - mae: 1.6319 
Epoch 394/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3664 - mae: 1.5995 
Epoch 395/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8452 - mae: 1.5705 
Epoch 396/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1546 - mae: 1.7064 
Epoch 397/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7117 - mae: 1.6970 
Epoch 398/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6622 - mae: 1.5288 
Epoch 399/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9905 - mae: 1.5109 
Epoch 400/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5553 - mae: 1.5088 
Epoch 401/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2241 - mae: 1.5894 
Epoch 402/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9552 - mae: 1.6867 
Epoch 403/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8616 - mae: 1.7147  
Epoch 404/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6028 - mae: 1.6715 
Epoch 405/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3296 - mae: 1.5118 
Epoch 406/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6093 - mae: 1.6317  
Epoch 407/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8440 - mae: 1.4820 
Epoch 408/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4591 - mae: 1.5597 
Epoch 409/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9434 - mae: 1.4812 
Epoch 410/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5675 - mae: 1.5753 
Epoch 411/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6233 - mae: 1.4234 
Epoch 412/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8615 - mae: 1.4194 
Epoch 413/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3310 - mae: 1.5204 
Epoch 414/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7428 - mae: 1.5519 
Epoch 415/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2236 - mae: 1.6342 
Epoch 416/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8963 - mae: 1.5419 
Epoch 417/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7184 - mae: 1.5612 
Epoch 418/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6425 - mae: 1.5444 
Epoch 419/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2338 - mae: 1.5956 
Epoch 420/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1304 - mae: 1.6586 
Epoch 421/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6684 - mae: 1.5646 
Epoch 422/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2657 - mae: 1.5120 
Epoch 423/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0610 - mae: 1.6318 
Epoch 424/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0312 - mae: 1.6603  
Epoch 425/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4145 - mae: 1.6181  
Epoch 426/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2241 - mae: 1.6323 
Epoch 427/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0105 - mae: 1.4643 
Epoch 428/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0263 - mae: 1.5387 
Epoch 429/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8204 - mae: 1.5309 
Epoch 430/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9397 - mae: 1.4441 
Epoch 431/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8087 - mae: 1.5140 
Epoch 432/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0648 - mae: 1.4644  
Epoch 433/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3057 - mae: 1.5018 
Epoch 434/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8582 - mae: 1.4008 
Epoch 435/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8165 - mae: 1.4377 
Epoch 436/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1185 - mae: 1.4699 
Epoch 437/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5749 - mae: 1.5116 
Epoch 438/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9733 - mae: 1.5844 
Epoch 439/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4861 - mae: 1.4467 
Epoch 440/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8616 - mae: 1.3272 
Epoch 441/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1900 - mae: 1.6252 
Epoch 442/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5820 - mae: 1.3972 
Epoch 443/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0918 - mae: 1.4767 
Epoch 444/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3299 - mae: 1.5987  
Epoch 445/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7869 - mae: 1.5129  
Epoch 446/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9886 - mae: 1.5265 
Epoch 447/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6581 - mae: 1.4699 
Epoch 448/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6576 - mae: 1.5441 
Epoch 449/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1280 - mae: 1.4364 
Epoch 450/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6271 - mae: 1.5258 
Epoch 451/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9385 - mae: 1.4117 
Epoch 452/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5694 - mae: 1.3875 
Epoch 453/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5401 - mae: 1.4993 
Epoch 454/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9672 - mae: 1.4045 
Epoch 455/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9416 - mae: 1.4278 
Epoch 456/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3139 - mae: 1.4943 
Epoch 457/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4715 - mae: 1.4818 
Epoch 458/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4714 - mae: 1.3555 
Epoch 459/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6679 - mae: 1.3837 
Epoch 460/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3692 - mae: 1.4775 
Epoch 461/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9616 - mae: 1.4848 
Epoch 462/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2197 - mae: 1.4827 
Epoch 463/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6465 - mae: 1.3731 
Epoch 464/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1985 - mae: 1.4664 
Epoch 465/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8643 - mae: 1.4402 
Epoch 466/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3455 - mae: 1.4653 
Epoch 467/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3018 - mae: 1.5030 
Epoch 468/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1616 - mae: 1.5486 
Epoch 469/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8834 - mae: 1.3952 
Epoch 470/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8562 - mae: 1.4746 
Epoch 471/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5395 - mae: 1.4132 
Epoch 472/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8587 - mae: 1.3960 
Epoch 473/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0071 - mae: 1.3938 
Epoch 474/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6593 - mae: 1.3721 
Epoch 475/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1358 - mae: 1.4420 
Epoch 476/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3344 - mae: 1.4666 
Epoch 477/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2943 - mae: 1.3883 
Epoch 478/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1035 - mae: 1.3060 
Epoch 479/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8962 - mae: 1.3939 
Epoch 480/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9681 - mae: 1.2708 
Epoch 481/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0422 - mae: 1.4280 
Epoch 482/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0126 - mae: 1.3127 
Epoch 483/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0385 - mae: 1.5372 
Epoch 484/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0688 - mae: 1.3264 
Epoch 485/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0267 - mae: 1.4433 
Epoch 486/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7391 - mae: 1.4071 
Epoch 487/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9989 - mae: 1.4683 
Epoch 488/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5448 - mae: 1.6161 
Epoch 489/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2658 - mae: 1.4413 
Epoch 490/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3288 - mae: 1.3699 
Epoch 491/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3687 - mae: 1.3123 
Epoch 492/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3377 - mae: 1.4158 
Epoch 493/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4964 - mae: 1.3429 
Epoch 494/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1610 - mae: 1.3191 
Epoch 495/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9518 - mae: 1.0940 
Epoch 496/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3821 - mae: 1.4393 
Epoch 497/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3060 - mae: 1.3377 
Epoch 498/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7516 - mae: 1.3700 
Epoch 499/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3595 - mae: 1.3024 
Epoch 500/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8172 - mae: 1.5220 

Model evaluation:
Loss (MSE): 4.56, MAE: 1.35
In [46]:
models = {
    "Linear Regression": LinearRegression(),
    "Lasso": Lasso(),
    "K-Neighbors Regressor": KNeighborsRegressor(),
    "Decision Tree": DecisionTreeRegressor(),
     "Random Forest Regressor": RandomForestRegressor(),
     "Gradient Boosting": GradientBoostingRegressor(),
     "XGBRegressor": XGBRegressor(),
     "CatBoosting Regressor": CatBoostRegressor(verbose=0, iterations = 100),
     "AdaBoost Regressor": AdaBoostRegressor(),
    "ExtraTreesRegressor": ExtraTreesRegressor(),
    "Support Vector Regressor(RBF)": SVR(kernel="rbf"),
    "Support Vector Regressor(linear)": SVR(kernel="linear"),
    "Nu SVR(rbf)": NuSVR(kernel="rbf"),
    "ANN": ANN_model
}
In [47]:
def safe_flatten(y_pred):
    """
    Flattens the array if it's a 2D array with shape (n, 1).
    Useful for ANN predictions.
    """
    if isinstance(y_pred, (np.ndarray, list)) and len(np.shape(y_pred)) == 2 and y_pred.shape[1] == 1:
        return y_pred.flatten()
    return y_pred
In [48]:
r2_train_score = {}
r2_test_score = {}
def evaluate_model(models, X_train, y_train, X_val, y_val):
    for model_name, model in models.items():
        model.fit(X_train, y_train)
        
        y_train_pred = model.predict(X_train)
        y_test_pred = model.predict(X_val)

        y = y_val
        y_pred = safe_flatten(y_test_pred)

        plt.figure(figsize=(8, 6))
        r2 = r2_score(y, y_pred)
        
        sns.scatterplot(x=y, y=y_pred, label='Predicted vs Actual', color='blue')
        sns.regplot(x=y, y=y_pred, scatter=False, label='Regression Line', color='red', ci=None)
        
        plt.xlabel('Actual Values')
        plt.ylabel('Predicted Values')
        plt.title(f'CO Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model')
        plt.legend()
        plt.grid(True)
        plt.tight_layout()
        plt.savefig(f'CO Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model.png')
        plt.show()
        
        r2_train_score[model_name] = r2_score(y_train, y_train_pred)
        r2_test_score[model_name] = r2_score(y_val, y_test_pred)
In [49]:
evaluate_model(models, X_train_scaled, y_train.CO, X_val_scaled, y_val.CO)

10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2083 - mae: 1.4006 
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 18ms/step
4/4 ━━━━━━━━━━━━━━━━━━━━ 0s 81ms/step
In [50]:
score = pd.DataFrame(list(zip(models.keys(), r2_train_score.values(), r2_test_score.values())), columns=["Model","r2_train_score", "r2_test_score"])
score
Out[50]:
Model r2_train_score r2_test_score
0 Linear Regression 0.298496 0.310329
1 Lasso 0.205461 0.198758
2 K-Neighbors Regressor 0.794460 0.706655
3 Decision Tree 0.997006 0.731715
4 Random Forest Regressor 0.970487 0.827927
5 Gradient Boosting 0.919220 0.797646
6 XGBRegressor 0.996926 0.788515
7 CatBoosting Regressor 0.968410 0.845676
8 AdaBoost Regressor 0.746776 0.719574
9 ExtraTreesRegressor 0.997006 0.844978
10 Support Vector Regressor(RBF) 0.473190 0.456430
11 Support Vector Regressor(linear) 0.253874 0.261680
12 Nu SVR(rbf) 0.433602 0.404798
13 ANN 0.943367 0.822314
In [51]:
# Set positions
x = np.arange(len(score['Model']))
width = 0.35  # Width of the bars

# Create plot
fig, ax = plt.subplots(figsize=(16, 8))
bars1 = ax.bar(x - width/2, score['r2_train_score'], width, label='Train R²', color='skyblue')
bars2 = ax.bar(x + width/2, score['r2_test_score'], width, label='Validation R²', color='salmon')

# Add labels and title
ax.set_xlabel('ML Models')
ax.set_ylabel('R² Score')
ax.set_title('CO Train vs Validation R² Score for Different Models')
ax.set_xticks(x)
ax.set_xticklabels(score['Model'], rotation=45)
ax.legend()

# Add R2 score text on top of bars
for bar in bars1 + bars2:
    yval = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2.0, yval + 0.01, f'{yval:.2f}', ha='center', va='bottom')

plt.tight_layout()
plt.savefig("CO Train vs Validation R² Score for Different Models")
plt.show()

Predicting the value of CO2¶

In [52]:
ANN_model = Sequential([
    Dense(32, input_dim=13),                  # No activation here
    LeakyReLU(alpha=0.1),                    # LeakyReLU activation
    Dense(32, activation='tanh'),            # Tanh for richer non-linearity
    Dense(16, activation='relu'),            # ReLU for simplicity
    Dense(1, activation='linear')            # Linear for regression output
])

# Compile the model
ANN_model.compile(optimizer='adam',
              loss='mean_squared_error',
              metrics=['mae'])


# Train the model
ANN_model.fit(X_train_scaled, y_train.CO2, epochs=500, verbose=1)

# Evaluate the model
loss, mae = ANN_model.evaluate(X_train_scaled, y_train.CO2, verbose=0)
print(f"\nModel evaluation:\nLoss (MSE): {loss:.2f}, MAE: {mae:.2f}")

Epoch 1/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 2s 35ms/step - loss: 971.2888 - mae: 29.2199
Epoch 2/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 852.4738 - mae: 27.1535 
Epoch 3/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 897.0617 - mae: 27.5853 
Epoch 4/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 816.9807 - mae: 26.5347 
Epoch 5/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 758.8616 - mae: 25.5917 
Epoch 6/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 720.9613 - mae: 24.7938 
Epoch 7/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 647.0811 - mae: 23.1684 
Epoch 8/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 618.7953 - mae: 22.4222 
Epoch 9/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 553.5217 - mae: 21.1887 
Epoch 10/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 463.5688 - mae: 18.8825 
Epoch 11/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 391.7823 - mae: 17.1454 
Epoch 12/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 332.0067 - mae: 15.5609 
Epoch 13/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 268.2933 - mae: 13.7168 
Epoch 14/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 217.2852 - mae: 12.0998 
Epoch 15/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 192.3208 - mae: 11.0861 
Epoch 16/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 163.3085 - mae: 10.0014 
Epoch 17/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 148.8390 - mae: 9.6554  
Epoch 18/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 129.5284 - mae: 8.8581 
Epoch 19/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 111.0075 - mae: 8.3567
Epoch 20/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 109.2474 - mae: 8.3348 
Epoch 21/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 111.4418 - mae: 8.3495 
Epoch 22/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 100.5414 - mae: 8.0990 
Epoch 23/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 87.0583 - mae: 7.3503 
Epoch 24/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 91.5189 - mae: 7.5758 
Epoch 25/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 86.7589 - mae: 7.2348 
Epoch 26/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 80.0594 - mae: 6.9449 
Epoch 27/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 79.8378 - mae: 6.9428 
Epoch 28/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 78.9295 - mae: 6.8522 
Epoch 29/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 68.9338 - mae: 6.3111 
Epoch 30/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 71.8124 - mae: 6.5123 
Epoch 31/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 69.4678 - mae: 6.3512 
Epoch 32/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 70.8776 - mae: 6.6940 
Epoch 33/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 61.6333 - mae: 6.1062 
Epoch 34/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 61.0036 - mae: 6.1099 
Epoch 35/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 58.2509 - mae: 5.9578 
Epoch 36/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 60.7742 - mae: 6.0740 
Epoch 37/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 60.5848 - mae: 6.0946 
Epoch 38/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 59.7367 - mae: 6.1034 
Epoch 39/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 56.5720 - mae: 5.7739 
Epoch 40/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 51.8915 - mae: 5.7104 
Epoch 41/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 47.9939 - mae: 5.3694 
Epoch 42/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 51.5936 - mae: 5.5273 
Epoch 43/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 49.7496 - mae: 5.5159 
Epoch 44/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 46.5658 - mae: 5.2398 
Epoch 45/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 51.0932 - mae: 5.5899 
Epoch 46/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 50.0542 - mae: 5.4831 
Epoch 47/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 42.8194 - mae: 5.0390 
Epoch 48/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 44.5907 - mae: 5.0486 
Epoch 49/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 40.4311 - mae: 4.8723 
Epoch 50/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 41.4721 - mae: 4.8772 
Epoch 51/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 42.0994 - mae: 4.8855 
Epoch 52/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.5851 - mae: 4.5207 
Epoch 53/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 34.4494 - mae: 4.3824 
Epoch 54/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.7001 - mae: 4.6922 
Epoch 55/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.5776 - mae: 4.2685 
Epoch 56/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.6299 - mae: 4.5828 
Epoch 57/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.6874 - mae: 4.2509 
Epoch 58/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.1981 - mae: 4.1700 
Epoch 59/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 30.9978 - mae: 4.0709 
Epoch 60/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.9333 - mae: 4.3929 
Epoch 61/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.1816 - mae: 4.3212 
Epoch 62/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 29.9763 - mae: 4.0720 
Epoch 63/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 30.6256 - mae: 4.1386 
Epoch 64/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 30.9484 - mae: 4.0547 
Epoch 65/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 31.5012 - mae: 4.1652 
Epoch 66/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 30.0958 - mae: 4.1425 
Epoch 67/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 29.2075 - mae: 4.0200 
Epoch 68/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.8771 - mae: 3.7245 
Epoch 69/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.5529 - mae: 3.7960 
Epoch 70/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.2648 - mae: 3.8462 
Epoch 71/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.0162 - mae: 3.6635 
Epoch 72/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.9976 - mae: 3.8432 
Epoch 73/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.6230 - mae: 3.9056 
Epoch 74/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.1281 - mae: 3.7212 
Epoch 75/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.9558 - mae: 3.6680 
Epoch 76/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.2152 - mae: 3.6010 
Epoch 77/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.6198 - mae: 3.6775 
Epoch 78/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.1574 - mae: 3.5959 
Epoch 79/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 23.8615 - mae: 3.5766 
Epoch 80/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.8738 - mae: 3.5123 
Epoch 81/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.7147 - mae: 3.3153 
Epoch 82/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.0796 - mae: 3.4543 
Epoch 83/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.8496 - mae: 3.5379 
Epoch 84/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.4565 - mae: 3.5608 
Epoch 85/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.3060 - mae: 3.3647 
Epoch 86/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.5074 - mae: 3.4104 
Epoch 87/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.8676 - mae: 3.4403 
Epoch 88/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.6501 - mae: 3.4304 
Epoch 89/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.4576 - mae: 3.6158 
Epoch 90/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.9229 - mae: 3.1636 
Epoch 91/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.2548 - mae: 3.3057 
Epoch 92/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.4314 - mae: 3.3893 
Epoch 93/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.8139 - mae: 3.4199 
Epoch 94/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.8418 - mae: 3.2225 
Epoch 95/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.1343 - mae: 3.2271 
Epoch 96/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.3820 - mae: 3.3501 
Epoch 97/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.2544 - mae: 3.3067 
Epoch 98/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.9168 - mae: 3.1676 
Epoch 99/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.2320 - mae: 3.0297
Epoch 100/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.2101 - mae: 2.9583 
Epoch 101/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.3682 - mae: 3.0407 
Epoch 102/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.3420 - mae: 3.1874 
Epoch 103/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.1227 - mae: 3.0070 
Epoch 104/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.2004 - mae: 2.9861 
Epoch 105/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.6553 - mae: 3.2881 
Epoch 106/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.2212 - mae: 3.0393 
Epoch 107/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.5478 - mae: 3.0555 
Epoch 108/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.9787 - mae: 2.8014 
Epoch 109/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.3722 - mae: 2.9790 
Epoch 110/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.9630 - mae: 2.9683 
Epoch 111/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.1403 - mae: 2.9139 
Epoch 112/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.7631 - mae: 2.8454 
Epoch 113/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.0715 - mae: 2.8679 
Epoch 114/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.9353 - mae: 2.7678
Epoch 115/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.5872 - mae: 2.6647
Epoch 116/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.8832 - mae: 2.9775 
Epoch 117/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.1620 - mae: 2.9049 
Epoch 118/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.4629 - mae: 2.7852 
Epoch 119/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.3947 - mae: 2.7458 
Epoch 120/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.2059 - mae: 2.9202 
Epoch 121/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.6663 - mae: 2.7972 
Epoch 122/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.6063 - mae: 2.8079 
Epoch 123/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.0874 - mae: 2.7518 
Epoch 124/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.0720 - mae: 2.7614 
Epoch 125/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.9881 - mae: 2.6036 
Epoch 126/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.1759 - mae: 2.8811 
Epoch 127/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.9151 - mae: 2.7088 
Epoch 128/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.1569 - mae: 2.5561 
Epoch 129/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.2690 - mae: 2.6289 
Epoch 130/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.9103 - mae: 2.7369 
Epoch 131/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.0609 - mae: 2.6313
Epoch 132/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.4980 - mae: 2.5778 
Epoch 133/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.2210 - mae: 2.8224 
Epoch 134/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.4969 - mae: 2.7157 
Epoch 135/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.0033 - mae: 2.5776 
Epoch 136/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.7156 - mae: 2.6401 
Epoch 137/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.5318 - mae: 2.4864
Epoch 138/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.9124 - mae: 2.5416 
Epoch 139/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.7044 - mae: 2.5440 
Epoch 140/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.0762 - mae: 2.5628
Epoch 141/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2069 - mae: 2.3918 
Epoch 142/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.0423 - mae: 2.5190 
Epoch 143/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.3621 - mae: 2.4933 
Epoch 144/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.5408 - mae: 2.6112 
Epoch 145/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.4501 - mae: 2.5153 
Epoch 146/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.4330 - mae: 2.5991 
Epoch 147/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.7644 - mae: 2.6010 
Epoch 148/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.3841 - mae: 2.7626 
Epoch 149/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.6525 - mae: 2.6328 
Epoch 150/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.1399 - mae: 2.4120
Epoch 151/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.3692 - mae: 2.5149 
Epoch 152/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.7281 - mae: 2.5431 
Epoch 153/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.6275 - mae: 2.5051 
Epoch 154/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.4432 - mae: 2.2807
Epoch 155/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9748 - mae: 2.3453 
Epoch 156/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.0870 - mae: 2.4460 
Epoch 157/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8200 - mae: 2.4027 
Epoch 158/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.0411 - mae: 2.6307 
Epoch 159/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.3464 - mae: 2.3642 
Epoch 160/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.6200 - mae: 2.4659 
Epoch 161/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.4703 - mae: 2.4894 
Epoch 162/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.5924 - mae: 2.4790 
Epoch 163/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8639 - mae: 2.2974
Epoch 164/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.4208 - mae: 2.1181
Epoch 165/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.0252 - mae: 2.4600 
Epoch 166/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.9212 - mae: 2.1351 
Epoch 167/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.3777 - mae: 2.3104 
Epoch 168/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.3606 - mae: 2.3175 
Epoch 169/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.8797 - mae: 2.4185 
Epoch 170/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9267 - mae: 2.3343
Epoch 171/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.4147 - mae: 2.2555
Epoch 172/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.4776 - mae: 2.2484 
Epoch 173/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.1689 - mae: 2.2583 
Epoch 174/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5471 - mae: 2.1853
Epoch 175/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.5190 - mae: 2.2610 
Epoch 176/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3570 - mae: 2.2011
Epoch 177/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.9849 - mae: 2.1909
Epoch 178/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.0885 - mae: 2.4585
Epoch 179/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8020 - mae: 2.2282
Epoch 180/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.2670 - mae: 2.0816 
Epoch 181/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.3236 - mae: 2.3666 
Epoch 182/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7998 - mae: 2.1369  
Epoch 183/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.5325 - mae: 2.2095 
Epoch 184/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.1959 - mae: 2.2341 
Epoch 185/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3149 - mae: 1.9905 
Epoch 186/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.9661 - mae: 2.1494 
Epoch 187/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4774 - mae: 2.0671 
Epoch 188/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.7935 - mae: 2.1519 
Epoch 189/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0832 - mae: 2.0469 
Epoch 190/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.5842 - mae: 2.2187 
Epoch 191/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2557 - mae: 2.2303
Epoch 192/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.4438 - mae: 2.4122 
Epoch 193/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6123 - mae: 2.1208 
Epoch 194/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.2835 - mae: 2.0863 
Epoch 195/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1685 - mae: 2.0193 
Epoch 196/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4882 - mae: 2.0940  
Epoch 197/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7595 - mae: 2.2450  
Epoch 198/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4376 - mae: 2.1344 
Epoch 199/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4817 - mae: 2.0300 
Epoch 200/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4764 - mae: 2.1004 
Epoch 201/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1801 - mae: 1.9625 
Epoch 202/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5892 - mae: 1.9196 
Epoch 203/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.8965 - mae: 2.0705  
Epoch 204/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.9008 - mae: 2.0782 
Epoch 205/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6559 - mae: 2.1069 
Epoch 206/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.3891 - mae: 2.3166 
Epoch 207/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1082 - mae: 2.0022 
Epoch 208/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.9871 - mae: 2.0825  
Epoch 209/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3529 - mae: 1.9391 
Epoch 210/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.1020 - mae: 2.2488 
Epoch 211/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3521 - mae: 1.9769  
Epoch 212/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.4487 - mae: 2.0370 
Epoch 213/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5481 - mae: 1.9807 
Epoch 214/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.7472 - mae: 2.0314 
Epoch 215/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6581 - mae: 2.0228  
Epoch 216/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5184 - mae: 2.1394
Epoch 217/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.8058 - mae: 2.0452 
Epoch 218/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.0009 - mae: 2.0898
Epoch 219/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0937 - mae: 1.9801 
Epoch 220/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2267 - mae: 1.9356 
Epoch 221/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5747 - mae: 1.9111 
Epoch 222/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4456 - mae: 1.9373 
Epoch 223/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.2775 - mae: 2.0597 
Epoch 224/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8541 - mae: 1.9812 
Epoch 225/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.2441 - mae: 2.0272 
Epoch 226/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5037 - mae: 1.9547 
Epoch 227/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4962 - mae: 1.8930  
Epoch 228/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.2874 - mae: 2.1212 
Epoch 229/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4717 - mae: 1.8514 
Epoch 230/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8355 - mae: 1.8915 
Epoch 231/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3750 - mae: 2.0916 
Epoch 232/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1490 - mae: 1.8906 
Epoch 233/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3002 - mae: 1.9579  
Epoch 234/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7984 - mae: 2.0958  
Epoch 235/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1692 - mae: 1.9182 
Epoch 236/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9161 - mae: 1.8850 
Epoch 237/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0815 - mae: 1.7902 
Epoch 238/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.9475 - mae: 1.8997  
Epoch 239/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1444 - mae: 1.8783 
Epoch 240/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5430 - mae: 1.7544 
Epoch 241/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.2055 - mae: 1.9481  
Epoch 242/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3015 - mae: 1.8329 
Epoch 243/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6849 - mae: 1.8838 
Epoch 244/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4790 - mae: 1.8495 
Epoch 245/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7190 - mae: 1.7190 
Epoch 246/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8855 - mae: 1.7971 
Epoch 247/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3038 - mae: 1.8482 
Epoch 248/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7046 - mae: 1.8109 
Epoch 249/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.4530 - mae: 2.0775 
Epoch 250/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8558 - mae: 1.8351 
Epoch 251/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.9916 - mae: 1.8844  
Epoch 252/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4748 - mae: 1.7468 
Epoch 253/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2290 - mae: 1.7803 
Epoch 254/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4913 - mae: 1.9282 
Epoch 255/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8452 - mae: 1.7730  
Epoch 256/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.0628 - mae: 2.0318 
Epoch 257/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4110 - mae: 1.7346 
Epoch 258/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6398 - mae: 1.7761  
Epoch 259/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6387 - mae: 1.8866  
Epoch 260/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6706 - mae: 1.7465 
Epoch 261/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8878 - mae: 1.7770 
Epoch 262/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0254 - mae: 1.6201 
Epoch 263/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8832 - mae: 1.7164 
Epoch 264/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2701 - mae: 1.6343 
Epoch 265/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8577 - mae: 1.6951 
Epoch 266/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3830 - mae: 1.6601 
Epoch 267/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4352 - mae: 1.8036 
Epoch 268/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6837 - mae: 1.5982 
Epoch 269/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6979 - mae: 1.8353 
Epoch 270/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5122 - mae: 1.8066 
Epoch 271/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5986 - mae: 1.9211  
Epoch 272/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8995 - mae: 1.6526 
Epoch 273/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9973 - mae: 1.6490 
Epoch 274/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4369 - mae: 1.8217 
Epoch 275/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9303 - mae: 1.7830 
Epoch 276/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5646 - mae: 1.5765 
Epoch 277/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2120 - mae: 1.7956 
Epoch 278/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3433 - mae: 1.6544 
Epoch 279/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2514 - mae: 1.7489 
Epoch 280/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5568 - mae: 1.5493 
Epoch 281/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0587 - mae: 1.7983 
Epoch 282/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0866 - mae: 1.6224 
Epoch 283/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4047 - mae: 1.6550 
Epoch 284/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4559 - mae: 1.5546 
Epoch 285/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5079 - mae: 1.7009  
Epoch 286/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3476 - mae: 1.6061 
Epoch 287/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7504 - mae: 1.7274  
Epoch 288/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5816 - mae: 1.5574 
Epoch 289/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9951 - mae: 1.4785 
Epoch 290/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1414 - mae: 1.7702 
Epoch 291/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3082 - mae: 1.6775 
Epoch 292/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0973 - mae: 1.6481 
Epoch 293/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4175 - mae: 1.6994 
Epoch 294/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1808 - mae: 1.5151 
Epoch 295/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1450 - mae: 1.6905  
Epoch 296/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5129 - mae: 1.6516  
Epoch 297/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2998 - mae: 1.5275 
Epoch 298/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7479 - mae: 1.6161 
Epoch 299/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9996 - mae: 1.7880  
Epoch 300/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3400 - mae: 1.7190  
Epoch 301/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9777 - mae: 1.5937 
Epoch 302/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6385 - mae: 1.5787 
Epoch 303/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9573 - mae: 1.5735 
Epoch 304/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2948 - mae: 1.6373 
Epoch 305/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1615 - mae: 1.6629  
Epoch 306/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7874 - mae: 1.5453 
Epoch 307/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8065 - mae: 1.5868 
Epoch 308/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2587 - mae: 1.6026 
Epoch 309/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9954 - mae: 1.5823 
Epoch 310/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6083 - mae: 1.5630 
Epoch 311/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7552 - mae: 1.5777 
Epoch 312/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4293 - mae: 1.6808 
Epoch 313/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5544 - mae: 1.5292 
Epoch 314/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4557 - mae: 1.6062  
Epoch 315/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9868 - mae: 1.6614  
Epoch 316/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8995 - mae: 1.6366  
Epoch 317/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6834 - mae: 1.7046 
Epoch 318/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1383 - mae: 1.4794 
Epoch 319/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2462 - mae: 1.7361  
Epoch 320/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3038 - mae: 1.5985 
Epoch 321/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3879 - mae: 1.6180 
Epoch 322/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8458 - mae: 1.4285 
Epoch 323/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5357 - mae: 1.5509 
Epoch 324/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1007 - mae: 1.4541 
Epoch 325/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1960 - mae: 1.6208 
Epoch 326/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4680 - mae: 1.6208 
Epoch 327/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2393 - mae: 1.5900 
Epoch 328/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6625 - mae: 1.6448  
Epoch 329/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1893 - mae: 1.4869 
Epoch 330/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4496 - mae: 1.6037 
Epoch 331/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5337 - mae: 1.5596 
Epoch 332/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7843 - mae: 1.4812 
Epoch 333/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4153 - mae: 1.4262 
Epoch 334/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5445 - mae: 1.5814 
Epoch 335/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8357 - mae: 1.4996 
Epoch 336/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6801 - mae: 1.4415 
Epoch 337/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1378 - mae: 1.4871 
Epoch 338/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6847 - mae: 1.4104 
Epoch 339/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9131 - mae: 1.5580 
Epoch 340/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9565 - mae: 1.4353 
Epoch 341/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8498 - mae: 1.5372  
Epoch 342/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0900 - mae: 1.3510 
Epoch 343/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1917 - mae: 1.3814 
Epoch 344/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5951 - mae: 1.6742 
Epoch 345/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3282 - mae: 1.5771 
Epoch 346/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1270 - mae: 1.5676 
Epoch 347/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8063 - mae: 1.4751 
Epoch 348/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1419 - mae: 1.4780 
Epoch 349/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6075 - mae: 1.4363 
Epoch 350/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9445 - mae: 1.6153 
Epoch 351/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9041 - mae: 1.4446 
Epoch 352/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3984 - mae: 1.4507 
Epoch 353/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5721 - mae: 1.3950 
Epoch 354/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5171 - mae: 1.4611 
Epoch 355/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4113 - mae: 1.4118 
Epoch 356/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3245 - mae: 1.4215 
Epoch 357/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5887 - mae: 1.4132 
Epoch 358/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3381 - mae: 1.3816 
Epoch 359/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0401 - mae: 1.4428 
Epoch 360/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0631 - mae: 1.3788 
Epoch 361/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8212 - mae: 1.3277 
Epoch 362/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0555 - mae: 1.3261 
Epoch 363/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5322 - mae: 1.5030 
Epoch 364/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6724 - mae: 1.4122 
Epoch 365/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6798 - mae: 1.2705 
Epoch 366/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4965 - mae: 1.4465 
Epoch 367/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9848 - mae: 1.5121 
Epoch 368/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3719 - mae: 1.3907 
Epoch 369/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2816 - mae: 1.5213 
Epoch 370/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9949 - mae: 1.4026 
Epoch 371/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9851 - mae: 1.3146 
Epoch 372/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3247 - mae: 1.3346 
Epoch 373/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9048 - mae: 1.4235 
Epoch 374/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6048 - mae: 1.3795 
Epoch 375/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4579 - mae: 1.3860 
Epoch 376/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8634 - mae: 1.4452 
Epoch 377/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1517 - mae: 1.3574 
Epoch 378/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2342 - mae: 1.3538 
Epoch 379/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6875 - mae: 1.2499 
Epoch 380/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7139 - mae: 1.4557 
Epoch 381/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2517 - mae: 1.3641 
Epoch 382/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7263 - mae: 1.3114 
Epoch 383/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9610 - mae: 1.3465 
Epoch 384/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2614 - mae: 1.3837 
Epoch 385/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6555 - mae: 1.3245 
Epoch 386/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5731 - mae: 1.2716 
Epoch 387/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6035 - mae: 1.2559 
Epoch 388/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9466 - mae: 1.3130 
Epoch 389/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7162 - mae: 1.3086 
Epoch 390/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2872 - mae: 1.3825 
Epoch 391/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8216 - mae: 1.3094 
Epoch 392/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0992 - mae: 1.3243 
Epoch 393/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1449 - mae: 1.3785 
Epoch 394/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4618 - mae: 1.2883 
Epoch 395/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2395 - mae: 1.3246 
Epoch 396/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0993 - mae: 1.4730 
Epoch 397/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6924 - mae: 1.3545 
Epoch 398/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3691 - mae: 1.2995 
Epoch 399/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3088 - mae: 1.4101 
Epoch 400/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3511 - mae: 1.3670 
Epoch 401/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0112 - mae: 1.1808 
Epoch 402/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9660 - mae: 1.3799 
Epoch 403/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3204 - mae: 1.3924 
Epoch 404/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7151 - mae: 1.4387 
Epoch 405/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5842 - mae: 1.3089 
Epoch 406/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5408 - mae: 1.2232 
Epoch 407/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8837 - mae: 1.3776 
Epoch 408/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3237 - mae: 1.2180 
Epoch 409/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5438 - mae: 1.2280 
Epoch 410/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4568 - mae: 1.2425 
Epoch 411/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1387 - mae: 1.2141 
Epoch 412/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5948 - mae: 1.2478 
Epoch 413/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7701 - mae: 1.2903 
Epoch 414/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5363 - mae: 1.2619 
Epoch 415/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4231 - mae: 1.3960 
Epoch 416/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7197 - mae: 1.2733 
Epoch 417/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5718 - mae: 1.2698 
Epoch 418/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0565 - mae: 1.3469 
Epoch 419/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8988 - mae: 1.3756 
Epoch 420/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3467 - mae: 1.2158 
Epoch 421/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0864 - mae: 1.1702 
Epoch 422/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5471 - mae: 1.2711 
Epoch 423/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3762 - mae: 1.2385 
Epoch 424/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9435 - mae: 1.1619 
Epoch 425/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5551 - mae: 1.2723 
Epoch 426/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3297 - mae: 1.2077 
Epoch 427/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4316 - mae: 1.2040 
Epoch 428/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5978 - mae: 1.2283 
Epoch 429/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0620 - mae: 1.3176 
Epoch 430/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6120 - mae: 1.2527 
Epoch 431/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9489 - mae: 1.1274 
Epoch 432/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0323 - mae: 1.1358 
Epoch 433/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6807 - mae: 1.2623 
Epoch 434/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3513 - mae: 1.2409 
Epoch 435/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1069 - mae: 1.1686 
Epoch 436/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4444 - mae: 1.2657 
Epoch 437/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4500 - mae: 1.2091 
Epoch 438/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4079 - mae: 1.2678 
Epoch 439/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7399 - mae: 1.3023 
Epoch 440/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0229 - mae: 1.1778 
Epoch 441/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3274 - mae: 1.3039 
Epoch 442/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2591 - mae: 1.4310 
Epoch 443/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9415 - mae: 1.1745 
Epoch 444/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1815 - mae: 1.1642 
Epoch 445/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4405 - mae: 1.2523 
Epoch 446/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2674 - mae: 1.2074 
Epoch 447/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3782 - mae: 1.2488 
Epoch 448/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4201 - mae: 1.2361 
Epoch 449/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2412 - mae: 1.1798 
Epoch 450/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4753 - mae: 1.2491 
Epoch 451/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1766 - mae: 1.2141 
Epoch 452/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6090 - mae: 1.1063 
Epoch 453/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6247 - mae: 1.2676 
Epoch 454/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0500 - mae: 1.1991 
Epoch 455/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2092 - mae: 1.2090 
Epoch 456/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9525 - mae: 1.1511 
Epoch 457/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8282 - mae: 1.1367 
Epoch 458/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4477 - mae: 1.2370 
Epoch 459/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1320 - mae: 1.1776 
Epoch 460/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7906 - mae: 1.1366 
Epoch 461/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3138 - mae: 1.1546 
Epoch 462/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8742 - mae: 1.1510 
Epoch 463/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8489 - mae: 1.3753 
Epoch 464/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9239 - mae: 1.3710 
Epoch 465/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8718 - mae: 1.2453 
Epoch 466/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0790 - mae: 1.2103 
Epoch 467/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1677 - mae: 1.2274 
Epoch 468/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8808 - mae: 1.1586 
Epoch 469/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0288 - mae: 1.2021 
Epoch 470/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3804 - mae: 1.2241 
Epoch 471/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9097 - mae: 1.1423 
Epoch 472/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9170 - mae: 1.1410 
Epoch 473/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1063 - mae: 1.1809 
Epoch 474/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2666 - mae: 1.1760 
Epoch 475/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6668 - mae: 1.0715 
Epoch 476/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6267 - mae: 1.0357 
Epoch 477/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.4852 - mae: 1.0771 
Epoch 478/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0723 - mae: 1.1679 
Epoch 479/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3036 - mae: 1.1940 
Epoch 480/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2356 - mae: 1.1699 
Epoch 481/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.4397 - mae: 1.0586 
Epoch 482/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7236 - mae: 1.0969 
Epoch 483/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6191 - mae: 1.1835 
Epoch 484/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7650 - mae: 1.1274 
Epoch 485/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.5562 - mae: 1.1299 
Epoch 486/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3966 - mae: 1.2353 
Epoch 487/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7169 - mae: 1.1179 
Epoch 488/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0049 - mae: 1.1680 
Epoch 489/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7635 - mae: 1.1568 
Epoch 490/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4976 - mae: 1.2230 
Epoch 491/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8286 - mae: 1.1429 
Epoch 492/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9666 - mae: 1.1641 
Epoch 493/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9247 - mae: 1.1599 
Epoch 494/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0517 - mae: 1.1892 
Epoch 495/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8571 - mae: 1.1246 
Epoch 496/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7137 - mae: 1.0738 
Epoch 497/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6394 - mae: 1.0976 
Epoch 498/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.5173 - mae: 1.0678 
Epoch 499/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.4467 - mae: 1.0275 
Epoch 500/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7683 - mae: 1.1479 

Model evaluation:
Loss (MSE): 2.60, MAE: 1.06
In [53]:
models = {
    "Linear Regression": LinearRegression(),
    "Lasso": Lasso(),
    "K-Neighbors Regressor": KNeighborsRegressor(),
    "Decision Tree": DecisionTreeRegressor(),
     "Random Forest Regressor": RandomForestRegressor(),
     "Gradient Boosting": GradientBoostingRegressor(),
     "XGBRegressor": XGBRegressor(),
     "CatBoosting Regressor": CatBoostRegressor(verbose=0, iterations = 100),
     "AdaBoost Regressor": AdaBoostRegressor(),
    "ExtraTreesRegressor": ExtraTreesRegressor(),
    "Support Vector Regressor(RBF)": SVR(kernel="rbf"),
    "Support Vector Regressor(linear)": SVR(kernel="linear"),
    "Nu SVR(rbf)": NuSVR(kernel="rbf"),
    "ANN": ANN_model
}
In [54]:
def safe_flatten(y_pred):
    """
    Flattens the array if it's a 2D array with shape (n, 1).
    Useful for ANN predictions.
    """
    if isinstance(y_pred, (np.ndarray, list)) and len(np.shape(y_pred)) == 2 and y_pred.shape[1] == 1:
        return y_pred.flatten()
    return y_pred
In [55]:
r2_train_score = {}
r2_test_score = {}
def evaluate_model(models, X_train, y_train, X_val, y_val):
    for model_name, model in models.items():
        model.fit(X_train, y_train)
        
        y_train_pred = model.predict(X_train)
        y_test_pred = model.predict(X_val)

        y = y_val
        y_pred = safe_flatten(y_test_pred)

        plt.figure(figsize=(8, 6))
        r2 = r2_score(y, y_pred)
        
        sns.scatterplot(x=y, y=y_pred, label='Predicted vs Actual', color='blue')
        sns.regplot(x=y, y=y_pred, scatter=False, label='Regression Line', color='red', ci=None)
        
        plt.xlabel('Actual Values')
        plt.ylabel('Predicted Values')
        plt.title(f'CO2 Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model')
        plt.legend()
        plt.grid(True)
        plt.tight_layout()
        plt.savefig(f'CO2 Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model.png')
        plt.show()
        
        r2_train_score[model_name] = r2_score(y_train, y_train_pred)
        r2_test_score[model_name] = r2_score(y_val, y_test_pred)
In [56]:
evaluate_model(models, X_train_scaled, y_train.CO2, X_val_scaled, y_val.CO2)

10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.3402 - mae: 1.0227 
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 12ms/step
4/4 ━━━━━━━━━━━━━━━━━━━━ 0s 20ms/step
In [57]:
score = pd.DataFrame(list(zip(models.keys(), r2_train_score.values(), r2_test_score.values())), columns=["Model","r2_train_score", "r2_test_score"])
score
Out[57]:
Model r2_train_score r2_test_score
0 Linear Regression 0.509402 0.542437
1 Lasso 0.452207 0.477392
2 K-Neighbors Regressor 0.838501 0.812381
3 Decision Tree 0.997671 0.771861
4 Random Forest Regressor 0.976996 0.876897
5 Gradient Boosting 0.941975 0.880438
6 XGBRegressor 0.997604 0.863107
7 CatBoosting Regressor 0.981642 0.885309
8 AdaBoost Regressor 0.833152 0.786018
9 ExtraTreesRegressor 0.997670 0.900201
10 Support Vector Regressor(RBF) 0.514539 0.543360
11 Support Vector Regressor(linear) 0.485929 0.502646
12 Nu SVR(rbf) 0.448582 0.462060
13 ANN 0.977113 0.871994
In [58]:
# Set positions
x = np.arange(len(score['Model']))
width = 0.35  # Width of the bars

# Create plot
fig, ax = plt.subplots(figsize=(16, 8))
bars1 = ax.bar(x - width/2, score['r2_train_score'], width, label='Train R²', color='skyblue')
bars2 = ax.bar(x + width/2, score['r2_test_score'], width, label='Validation R²', color='salmon')

# Add labels and title
ax.set_xlabel('ML Models')
ax.set_ylabel('R² Score')
ax.set_title('C02 Train vs Validation R² Score for Different Models')
ax.set_xticks(x)
ax.set_xticklabels(score['Model'], rotation=45)
ax.legend()

# Add R2 score text on top of bars
for bar in bars1 + bars2:
    yval = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2.0, yval + 0.01, f'{yval:.2f}', ha='center', va='bottom')

plt.tight_layout()
plt.savefig("CO2 Train vs Validation R² Score for Different Models")
plt.show()

Prediction for H2¶

In [59]:
ANN_model = Sequential([
    Dense(32, input_dim=13),                  # No activation here
    LeakyReLU(alpha=0.1),                    # LeakyReLU activation
    Dense(32, activation='tanh'),            # Tanh for richer non-linearity
    Dense(16, activation='relu'),            # ReLU for simplicity
    Dense(1, activation='linear')            # Linear for regression output
])

# Compile the model
ANN_model.compile(optimizer='adam',
              loss='mean_squared_error',
              metrics=['mae'])


# Train the model
ANN_model.fit(X_train_scaled, y_train.H2, epochs=500, verbose=1)

# Evaluate the model
loss, mae = ANN_model.evaluate(X_train_scaled, y_train.H2, verbose=0)
print(f"\nModel evaluation:\nLoss (MSE): {loss:.2f}, MAE: {mae:.2f}")

Epoch 1/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 2s 35ms/step - loss: 1114.5948 - mae: 30.6551
Epoch 2/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1092.6293 - mae: 30.3200
Epoch 3/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1016.1355 - mae: 29.1121
Epoch 4/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 950.2632 - mae: 27.9327 
Epoch 5/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 925.0381 - mae: 27.6578  
Epoch 6/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 782.8148 - mae: 25.2815 
Epoch 7/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 713.4860 - mae: 23.5926 
Epoch 8/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 617.4475 - mae: 21.3423 
Epoch 9/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 466.7102 - mae: 17.8205 
Epoch 10/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 379.0529 - mae: 15.9844 
Epoch 11/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 279.0497 - mae: 13.2619 
Epoch 12/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 233.6953 - mae: 11.6012
Epoch 13/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 185.0137 - mae: 10.2930 
Epoch 14/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 171.2313 - mae: 9.7690 
Epoch 15/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 135.7586 - mae: 8.6040 
Epoch 16/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 126.1504 - mae: 8.6905 
Epoch 17/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 110.9560 - mae: 7.9227 
Epoch 18/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 100.4794 - mae: 7.7887
Epoch 19/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 94.4140 - mae: 7.5600 
Epoch 20/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 89.3403 - mae: 7.3504 
Epoch 21/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 84.1876 - mae: 7.1113 
Epoch 22/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 77.9369 - mae: 6.9014 
Epoch 23/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 70.5678 - mae: 6.6286 
Epoch 24/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 70.5308 - mae: 6.5333 
Epoch 25/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 68.7351 - mae: 6.5970 
Epoch 26/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 66.9746 - mae: 6.4009 
Epoch 27/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 59.5299 - mae: 6.0411 
Epoch 28/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 63.8065 - mae: 6.2055 
Epoch 29/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 64.7406 - mae: 6.3353 
Epoch 30/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 58.8110 - mae: 6.0271 
Epoch 31/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 56.1725 - mae: 5.9506 
Epoch 32/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 51.9402 - mae: 5.6167 
Epoch 33/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 51.1221 - mae: 5.6004 
Epoch 34/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 56.9818 - mae: 5.9647 
Epoch 35/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 53.5437 - mae: 5.8061 
Epoch 36/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 45.4872 - mae: 5.2557 
Epoch 37/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 50.6648 - mae: 5.5402 
Epoch 38/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 50.1591 - mae: 5.5287 
Epoch 39/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 49.0068 - mae: 5.4025 
Epoch 40/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 40.5049 - mae: 4.8911 
Epoch 41/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 47.4356 - mae: 5.3942 
Epoch 42/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 39.6630 - mae: 4.9123 
Epoch 43/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 38.3502 - mae: 4.8363 
Epoch 44/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 42.1500 - mae: 4.9903 
Epoch 45/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 35.0358 - mae: 4.6555 
Epoch 46/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 35.1659 - mae: 4.7034 
Epoch 47/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 38.4428 - mae: 4.7524 
Epoch 48/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 34.3109 - mae: 4.4980 
Epoch 49/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 37.6402 - mae: 4.6525 
Epoch 50/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 39.7448 - mae: 4.8190 
Epoch 51/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.8882 - mae: 4.2895 
Epoch 52/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 31.5809 - mae: 4.3003 
Epoch 53/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 30.1885 - mae: 4.1537 
Epoch 54/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 34.3234 - mae: 4.3767 
Epoch 55/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 32.0350 - mae: 4.1690 
Epoch 56/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 34.1826 - mae: 4.2859 
Epoch 57/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 28.0954 - mae: 3.9268 
Epoch 58/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 29.0354 - mae: 4.0484 
Epoch 59/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 28.5883 - mae: 3.9239 
Epoch 60/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.4623 - mae: 3.7134 
Epoch 61/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 29.6323 - mae: 4.0048 
Epoch 62/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 27.1073 - mae: 3.8058 
Epoch 63/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 25.8526 - mae: 3.5992 
Epoch 64/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.4837 - mae: 3.5261 
Epoch 65/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.3290 - mae: 3.5894 
Epoch 66/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.3423 - mae: 3.4705 
Epoch 67/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 24.8294 - mae: 3.6171 
Epoch 68/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 22.2324 - mae: 3.4568 
Epoch 69/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.4214 - mae: 3.3360 
Epoch 70/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 23.1652 - mae: 3.4849 
Epoch 71/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.0867 - mae: 3.3631 
Epoch 72/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 21.4526 - mae: 3.2845 
Epoch 73/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.9731 - mae: 3.3159 
Epoch 74/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.9955 - mae: 3.1295
Epoch 75/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.0359 - mae: 3.1859 
Epoch 76/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 20.7746 - mae: 3.3432 
Epoch 77/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.9059 - mae: 3.1181 
Epoch 78/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 23.8073 - mae: 3.4327 
Epoch 79/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.2646 - mae: 3.1973 
Epoch 80/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.6540 - mae: 3.0792 
Epoch 81/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.8386 - mae: 3.1069 
Epoch 82/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.4348 - mae: 2.9877 
Epoch 83/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.3110 - mae: 2.9578 
Epoch 84/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.7106 - mae: 2.8899 
Epoch 85/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 19.1399 - mae: 3.1721 
Epoch 86/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.6142 - mae: 3.1050 
Epoch 87/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.1353 - mae: 2.8624 
Epoch 88/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.5072 - mae: 2.9965 
Epoch 89/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 18.2345 - mae: 2.9513 
Epoch 90/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.4015 - mae: 2.8102 
Epoch 91/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.4113 - mae: 2.8092 
Epoch 92/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.2828 - mae: 2.9984 
Epoch 93/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.9517 - mae: 2.5741 
Epoch 94/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.4109 - mae: 2.7929 
Epoch 95/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 15.1049 - mae: 2.7245
Epoch 96/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.1652 - mae: 2.8040 
Epoch 97/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9413 - mae: 2.5375
Epoch 98/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2699 - mae: 2.4382 
Epoch 99/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.3297 - mae: 2.6747 
Epoch 100/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.9504 - mae: 2.6735 
Epoch 101/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.0888 - mae: 2.6060 
Epoch 102/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 17.1756 - mae: 2.8884 
Epoch 103/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.7709 - mae: 2.5452
Epoch 104/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.8165 - mae: 2.5843 
Epoch 105/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8161 - mae: 2.4115
Epoch 106/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 13.2415 - mae: 2.5811
Epoch 107/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.4562 - mae: 2.3810
Epoch 108/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.0395 - mae: 2.5435 
Epoch 109/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.2404 - mae: 2.6316 
Epoch 110/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.0284 - mae: 2.4667
Epoch 111/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.0550 - mae: 2.5302 
Epoch 112/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.7273 - mae: 2.2651
Epoch 113/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.3233 - mae: 2.3046
Epoch 114/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.1697 - mae: 2.5089
Epoch 115/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9296 - mae: 2.3336
Epoch 116/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5377 - mae: 2.3086
Epoch 117/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8539 - mae: 2.3688
Epoch 118/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2646 - mae: 2.3152
Epoch 119/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.2454 - mae: 2.2108
Epoch 120/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.7935 - mae: 2.4377
Epoch 121/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8773 - mae: 2.3480 
Epoch 122/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.5365 - mae: 2.3916 
Epoch 123/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.1099 - mae: 2.2963
Epoch 124/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0959 - mae: 2.1998 
Epoch 125/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.5071 - mae: 2.5400 
Epoch 126/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4520 - mae: 2.2113 
Epoch 127/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 14.5461 - mae: 2.5842 
Epoch 128/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7880 - mae: 2.1922 
Epoch 129/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.1188 - mae: 2.2976 
Epoch 130/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.5429 - mae: 2.1590 
Epoch 131/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5511 - mae: 2.2351
Epoch 132/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1897 - mae: 2.2316 
Epoch 133/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6210 - mae: 2.2059 
Epoch 134/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.8312 - mae: 2.3434 
Epoch 135/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5395 - mae: 2.0961 
Epoch 136/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.9462 - mae: 2.2693 
Epoch 137/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3222 - mae: 2.2488
Epoch 138/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8143 - mae: 2.0755 
Epoch 139/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3606 - mae: 2.2161
Epoch 140/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.6472 - mae: 2.2352
Epoch 141/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0597 - mae: 2.1483 
Epoch 142/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7616 - mae: 2.0117 
Epoch 143/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.9447 - mae: 2.2432 
Epoch 144/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2080 - mae: 2.2716 
Epoch 145/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5173 - mae: 2.0969 
Epoch 146/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8170 - mae: 2.1970 
Epoch 147/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6614 - mae: 2.0495 
Epoch 148/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8627 - mae: 2.1863
Epoch 149/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6663 - mae: 2.0223 
Epoch 150/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3985 - mae: 2.1448
Epoch 151/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1086 - mae: 1.8983 
Epoch 152/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5836 - mae: 2.2107
Epoch 153/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.7922 - mae: 2.1377 
Epoch 154/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6874 - mae: 2.0690 
Epoch 155/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1593 - mae: 2.0107 
Epoch 156/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0320 - mae: 1.9707 
Epoch 157/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3945 - mae: 2.1413 
Epoch 158/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8443 - mae: 2.1230 
Epoch 159/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6169 - mae: 1.9797 
Epoch 160/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5259 - mae: 2.0268 
Epoch 161/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.4618 - mae: 2.0676 
Epoch 162/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.5185 - mae: 2.1594 
Epoch 163/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6301 - mae: 2.1115 
Epoch 164/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.0644 - mae: 2.0734 
Epoch 165/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.6315 - mae: 2.0954 
Epoch 166/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4702 - mae: 1.8991 
Epoch 167/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.9594 - mae: 2.2178 
Epoch 168/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3868 - mae: 2.0571 
Epoch 169/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3466 - mae: 2.1073 
Epoch 170/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1306 - mae: 1.8311 
Epoch 171/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.4727 - mae: 2.0563  
Epoch 172/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3707 - mae: 1.9968 
Epoch 173/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5698 - mae: 1.8581 
Epoch 174/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0879 - mae: 1.9908 
Epoch 175/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5890 - mae: 1.9101 
Epoch 176/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0711 - mae: 2.0736 
Epoch 177/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1819 - mae: 1.9321 
Epoch 178/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7444 - mae: 1.8828 
Epoch 179/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8824 - mae: 1.8847 
Epoch 180/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1463 - mae: 1.9676 
Epoch 181/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6734 - mae: 1.9029 
Epoch 182/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.2891 - mae: 2.0640 
Epoch 183/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.0317 - mae: 1.9968 
Epoch 184/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5230 - mae: 1.7912 
Epoch 185/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.7749 - mae: 2.1145 
Epoch 186/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9760 - mae: 1.9564 
Epoch 187/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2445 - mae: 1.8696 
Epoch 188/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.7488 - mae: 2.0677 
Epoch 189/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8752 - mae: 2.1372 
Epoch 190/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.0457 - mae: 2.1318 
Epoch 191/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.7947 - mae: 1.9966  
Epoch 192/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4591 - mae: 1.8224 
Epoch 193/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3937 - mae: 1.8791 
Epoch 194/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3974 - mae: 1.9366 
Epoch 195/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.8741 - mae: 1.9335  
Epoch 196/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4772 - mae: 1.7487 
Epoch 197/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8496 - mae: 1.8726  
Epoch 198/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9928 - mae: 1.8353 
Epoch 199/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2892 - mae: 1.7971 
Epoch 200/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.5112 - mae: 2.0260 
Epoch 201/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6729 - mae: 1.8387 
Epoch 202/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7752 - mae: 1.8458 
Epoch 203/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4857 - mae: 1.7732 
Epoch 204/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1225 - mae: 1.8155 
Epoch 205/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7576 - mae: 1.7890 
Epoch 206/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3094 - mae: 1.8439 
Epoch 207/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1064 - mae: 1.8149 
Epoch 208/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2610 - mae: 1.8466 
Epoch 209/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8052 - mae: 1.8042 
Epoch 210/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.3714 - mae: 1.8327 
Epoch 211/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8378 - mae: 1.8575  
Epoch 212/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9301 - mae: 1.7717 
Epoch 213/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.3973 - mae: 1.9402 
Epoch 214/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6419 - mae: 1.7870 
Epoch 215/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5429 - mae: 1.8089 
Epoch 216/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4012 - mae: 1.7884 
Epoch 217/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8683 - mae: 1.8049 
Epoch 218/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3755 - mae: 1.9024 
Epoch 219/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7541 - mae: 1.7697 
Epoch 220/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5222 - mae: 1.9829 
Epoch 221/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4539 - mae: 1.6469 
Epoch 222/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8794 - mae: 1.8283 
Epoch 223/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.5230 - mae: 1.8031  
Epoch 224/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6973 - mae: 1.7187 
Epoch 225/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2125 - mae: 1.6877 
Epoch 226/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8679 - mae: 1.7486 
Epoch 227/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6433 - mae: 1.7514 
Epoch 228/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6813 - mae: 1.7963  
Epoch 229/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2982 - mae: 1.8168  
Epoch 230/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3549 - mae: 1.8734 
Epoch 231/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7668 - mae: 1.6078 
Epoch 232/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3217 - mae: 1.6369 
Epoch 233/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.9218 - mae: 1.8939  
Epoch 234/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4267 - mae: 1.8587 
Epoch 235/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5288 - mae: 1.7924 
Epoch 236/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2114 - mae: 1.6976  
Epoch 237/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.7009 - mae: 1.9002 
Epoch 238/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 11.8370 - mae: 2.2791 
Epoch 239/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3312 - mae: 2.0411  
Epoch 240/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9957 - mae: 1.7641 
Epoch 241/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6234 - mae: 1.7176 
Epoch 242/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8208 - mae: 1.8211  
Epoch 243/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1348 - mae: 1.6715 
Epoch 244/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4715 - mae: 1.5996 
Epoch 245/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3844 - mae: 1.5969 
Epoch 246/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4936 - mae: 1.5854 
Epoch 247/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1469 - mae: 1.7919 
Epoch 248/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1041 - mae: 1.9110  
Epoch 249/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4767 - mae: 1.7406  
Epoch 250/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9387 - mae: 1.7127 
Epoch 251/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.9079 - mae: 1.8278  
Epoch 252/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0146 - mae: 1.6697  
Epoch 253/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3141 - mae: 1.5889 
Epoch 254/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9803 - mae: 1.6378 
Epoch 255/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1679 - mae: 1.6577 
Epoch 256/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.1172 - mae: 1.8403  
Epoch 257/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.7389 - mae: 1.7300  
Epoch 258/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9727 - mae: 1.5645 
Epoch 259/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.1053 - mae: 1.7054  
Epoch 260/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7324 - mae: 1.5636 
Epoch 261/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7702 - mae: 1.6606 
Epoch 262/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1102 - mae: 1.5558 
Epoch 263/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2187 - mae: 1.7529  
Epoch 264/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6487 - mae: 1.5869 
Epoch 265/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0549 - mae: 1.6875  
Epoch 266/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7540 - mae: 1.6745 
Epoch 267/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4513 - mae: 1.5995 
Epoch 268/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9412 - mae: 1.4961 
Epoch 269/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8305 - mae: 1.5548 
Epoch 270/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1986 - mae: 1.5340 
Epoch 271/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2205 - mae: 1.6794 
Epoch 272/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1818 - mae: 1.7159 
Epoch 273/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7046 - mae: 1.6881 
Epoch 274/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1028 - mae: 1.6782 
Epoch 275/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2425 - mae: 1.5443 
Epoch 276/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9231 - mae: 1.7119  
Epoch 277/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4070 - mae: 1.6104 
Epoch 278/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1086 - mae: 1.5280 
Epoch 279/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2192 - mae: 1.5742 
Epoch 280/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3833 - mae: 1.5374 
Epoch 281/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3732 - mae: 1.5216 
Epoch 282/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2961 - mae: 1.7057  
Epoch 283/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7185 - mae: 1.5384 
Epoch 284/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4435 - mae: 1.5106 
Epoch 285/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6901 - mae: 1.4351 
Epoch 286/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6154 - mae: 1.5610 
Epoch 287/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0514 - mae: 1.6623  
Epoch 288/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6747 - mae: 1.5369 
Epoch 289/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1263 - mae: 1.6442 
Epoch 290/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9073 - mae: 1.4977 
Epoch 291/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6469 - mae: 1.5811 
Epoch 292/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7845 - mae: 1.5949 
Epoch 293/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6975 - mae: 1.5618 
Epoch 294/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.5297 - mae: 1.5875  
Epoch 295/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1302 - mae: 1.6390 
Epoch 296/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7524 - mae: 1.8223 
Epoch 297/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0430 - mae: 1.6175 
Epoch 298/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6257 - mae: 1.5270 
Epoch 299/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8363 - mae: 1.6281 
Epoch 300/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5411 - mae: 1.5706 
Epoch 301/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9502 - mae: 1.6140 
Epoch 302/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2920 - mae: 1.6932 
Epoch 303/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6756 - mae: 1.4297 
Epoch 304/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1857 - mae: 1.5748 
Epoch 305/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2728 - mae: 1.4679 
Epoch 306/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3675 - mae: 1.5771 
Epoch 307/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1718 - mae: 1.5318 
Epoch 308/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5667 - mae: 1.5377 
Epoch 309/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3551 - mae: 1.4952 
Epoch 310/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1853 - mae: 1.5391 
Epoch 311/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4520 - mae: 1.5916 
Epoch 312/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7195 - mae: 1.4803 
Epoch 313/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1946 - mae: 1.4137 
Epoch 314/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3695 - mae: 1.5332 
Epoch 315/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7926 - mae: 1.5264 
Epoch 316/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0271 - mae: 1.3905 
Epoch 317/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1730 - mae: 1.5210 
Epoch 318/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4764 - mae: 1.5540  
Epoch 319/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4406 - mae: 1.6227  
Epoch 320/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9613 - mae: 1.4559 
Epoch 321/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2503 - mae: 1.5618 
Epoch 322/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1739 - mae: 1.4555 
Epoch 323/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0741 - mae: 1.5143 
Epoch 324/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5198 - mae: 1.4028 
Epoch 325/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2027 - mae: 1.5279 
Epoch 326/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5669 - mae: 1.4459 
Epoch 327/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7476 - mae: 1.4717 
Epoch 328/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.2202 - mae: 1.5584 
Epoch 329/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3472 - mae: 1.3975 
Epoch 330/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.8109 - mae: 1.8309 
Epoch 331/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8744 - mae: 1.8462 
Epoch 332/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4220 - mae: 1.7634  
Epoch 333/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1903 - mae: 1.5614 
Epoch 334/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4283 - mae: 1.3985 
Epoch 335/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3649 - mae: 1.5678 
Epoch 336/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6595 - mae: 1.5216 
Epoch 337/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0358 - mae: 1.5551 
Epoch 338/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2973 - mae: 1.4561 
Epoch 339/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9381 - mae: 1.4748 
Epoch 340/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9186 - mae: 1.4710 
Epoch 341/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5329 - mae: 1.5103  
Epoch 342/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9771 - mae: 1.4264 
Epoch 343/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9666 - mae: 1.4862 
Epoch 344/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9080 - mae: 1.5821  
Epoch 345/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7900 - mae: 1.4248 
Epoch 346/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7387 - mae: 1.3954 
Epoch 347/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0994 - mae: 1.3406 
Epoch 348/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3751 - mae: 1.3677 
Epoch 349/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8856 - mae: 1.5536  
Epoch 350/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1493 - mae: 1.6020  
Epoch 351/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0260 - mae: 1.4050  
Epoch 352/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3759 - mae: 1.4909 
Epoch 353/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1827 - mae: 1.5589 
Epoch 354/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5492 - mae: 1.3603 
Epoch 355/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6190 - mae: 1.4044 
Epoch 356/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0925 - mae: 1.4800  
Epoch 357/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5991 - mae: 1.5280 
Epoch 358/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7222 - mae: 1.3377 
Epoch 359/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8758 - mae: 1.3881 
Epoch 360/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4003 - mae: 1.6245 
Epoch 361/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0127 - mae: 1.6308 
Epoch 362/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0645 - mae: 1.4797 
Epoch 363/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5713 - mae: 1.3531 
Epoch 364/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1943 - mae: 1.5619  
Epoch 365/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1317 - mae: 1.3168 
Epoch 366/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1440 - mae: 1.3329 
Epoch 367/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6511 - mae: 1.2521 
Epoch 368/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7178 - mae: 1.3649 
Epoch 369/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3575 - mae: 1.4443 
Epoch 370/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1984 - mae: 1.4837 
Epoch 371/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3674 - mae: 1.3125 
Epoch 372/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0808 - mae: 1.5719 
Epoch 373/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3937 - mae: 1.4843  
Epoch 374/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2546 - mae: 1.3394 
Epoch 375/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8873 - mae: 1.3570 
Epoch 376/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1401 - mae: 1.4841 
Epoch 377/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9568 - mae: 1.3475 
Epoch 378/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5639 - mae: 1.4754 
Epoch 379/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5112 - mae: 1.3391  
Epoch 380/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8268 - mae: 1.5052 
Epoch 381/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4189 - mae: 1.3697 
Epoch 382/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5878 - mae: 1.4552 
Epoch 383/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2602 - mae: 1.4629 
Epoch 384/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9859 - mae: 1.5162 
Epoch 385/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9017 - mae: 1.4421 
Epoch 386/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3737 - mae: 1.3324 
Epoch 387/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1579 - mae: 1.4341 
Epoch 388/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8381 - mae: 1.3956 
Epoch 389/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6068 - mae: 1.3392 
Epoch 390/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.0883 - mae: 1.5154 
Epoch 391/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0760 - mae: 1.4329 
Epoch 392/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4054 - mae: 1.3992 
Epoch 393/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6088 - mae: 1.3354 
Epoch 394/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1086 - mae: 1.4613 
Epoch 395/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2313 - mae: 1.3339 
Epoch 396/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6489 - mae: 1.4291 
Epoch 397/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3589 - mae: 1.4099 
Epoch 398/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7635 - mae: 1.4131 
Epoch 399/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1867 - mae: 1.3617 
Epoch 400/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.7598 - mae: 1.4851  
Epoch 401/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2988 - mae: 1.3671  
Epoch 402/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1980 - mae: 1.4217  
Epoch 403/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.5735 - mae: 1.4791 
Epoch 404/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7590 - mae: 1.2944 
Epoch 405/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4735 - mae: 1.4001 
Epoch 406/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4777 - mae: 1.3710 
Epoch 407/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3769 - mae: 1.4488 
Epoch 408/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2930 - mae: 1.4899 
Epoch 409/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7755 - mae: 1.4520 
Epoch 410/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.2348 - mae: 1.7018  
Epoch 411/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6904 - mae: 1.5195 
Epoch 412/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.2407 - mae: 1.4353  
Epoch 413/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6604 - mae: 1.4202 
Epoch 414/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3496 - mae: 1.3409 
Epoch 415/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7143 - mae: 1.4181  
Epoch 416/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6167 - mae: 1.4812 
Epoch 417/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3187 - mae: 1.4134 
Epoch 418/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6760 - mae: 1.3625 
Epoch 419/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5245 - mae: 1.3557 
Epoch 420/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6400 - mae: 1.3385 
Epoch 421/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8596 - mae: 1.3417 
Epoch 422/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8839 - mae: 1.4252  
Epoch 423/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6442 - mae: 1.3479 
Epoch 424/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0663 - mae: 1.3204 
Epoch 425/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2858 - mae: 1.3499 
Epoch 426/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6484 - mae: 1.4001  
Epoch 427/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8568 - mae: 1.2545 
Epoch 428/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.9560 - mae: 1.7138 
Epoch 429/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3823 - mae: 1.7760 
Epoch 430/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4932 - mae: 1.5845 
Epoch 431/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9750 - mae: 1.4019 
Epoch 432/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9146 - mae: 1.2470 
Epoch 433/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5846 - mae: 1.3640 
Epoch 434/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1352 - mae: 1.3496 
Epoch 435/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2317 - mae: 1.3433 
Epoch 436/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2104 - mae: 1.3218 
Epoch 437/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.5484 - mae: 1.4964  
Epoch 438/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3031 - mae: 1.2997 
Epoch 439/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4299 - mae: 1.3499 
Epoch 440/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1646 - mae: 1.7112 
Epoch 441/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4181 - mae: 2.0311  
Epoch 442/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.9539 - mae: 1.6273 
Epoch 443/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.8833 - mae: 1.6443  
Epoch 444/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1876 - mae: 1.5861 
Epoch 445/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9827 - mae: 1.2888 
Epoch 446/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5678 - mae: 1.3328 
Epoch 447/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8111 - mae: 1.2426 
Epoch 448/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.6780 - mae: 1.4879  
Epoch 449/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4567 - mae: 1.2718 
Epoch 450/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9940 - mae: 1.3376 
Epoch 451/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5870 - mae: 1.2043 
Epoch 452/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8427 - mae: 1.3439 
Epoch 453/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7806 - mae: 1.3244 
Epoch 454/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1371 - mae: 1.3259 
Epoch 455/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7375 - mae: 1.2873 
Epoch 456/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7486 - mae: 1.2529 
Epoch 457/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0368 - mae: 1.1581 
Epoch 458/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.1106 - mae: 1.1513 
Epoch 459/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3723 - mae: 1.3469 
Epoch 460/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6502 - mae: 1.4341 
Epoch 461/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5956 - mae: 1.2854 
Epoch 462/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0966 - mae: 1.3140 
Epoch 463/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9249 - mae: 1.2941 
Epoch 464/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1178 - mae: 1.2350 
Epoch 465/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1492 - mae: 1.3006 
Epoch 466/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5485 - mae: 1.3094 
Epoch 467/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7805 - mae: 1.3461 
Epoch 468/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3751 - mae: 1.3163 
Epoch 469/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2850 - mae: 1.2175 
Epoch 470/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9013 - mae: 1.2812 
Epoch 471/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.8036 - mae: 1.3916 
Epoch 472/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9086 - mae: 1.3535 
Epoch 473/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6836 - mae: 1.4228  
Epoch 474/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2234 - mae: 1.3286  
Epoch 475/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2839 - mae: 1.2185 
Epoch 476/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2718 - mae: 1.2781 
Epoch 477/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2997 - mae: 1.2415 
Epoch 478/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3531 - mae: 1.2744 
Epoch 479/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9929 - mae: 1.3104 
Epoch 480/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4795 - mae: 1.3177 
Epoch 481/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2462 - mae: 1.3406 
Epoch 482/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.0282 - mae: 1.3370 
Epoch 483/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7476 - mae: 1.2154 
Epoch 484/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8581 - mae: 1.2283 
Epoch 485/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9911 - mae: 1.2803 
Epoch 486/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3683 - mae: 1.2385 
Epoch 487/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6179 - mae: 1.2705 
Epoch 488/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5909 - mae: 1.3205 
Epoch 489/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2040 - mae: 1.1651 
Epoch 490/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.6336 - mae: 1.2532 
Epoch 491/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5880 - mae: 1.2729 
Epoch 492/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1006 - mae: 1.2435 
Epoch 493/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5694 - mae: 1.1555 
Epoch 494/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1799 - mae: 1.2588 
Epoch 495/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7182 - mae: 1.2703 
Epoch 496/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7736 - mae: 1.2977 
Epoch 497/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7881 - mae: 1.2506 
Epoch 498/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7631 - mae: 1.2596 
Epoch 499/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2382 - mae: 1.1648 
Epoch 500/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4652 - mae: 1.2477 

Model evaluation:
Loss (MSE): 4.13, MAE: 1.23
In [60]:
models = {
    "Linear Regression": LinearRegression(),
    "Lasso": Lasso(),
    "K-Neighbors Regressor": KNeighborsRegressor(),
    "Decision Tree": DecisionTreeRegressor(),
     "Random Forest Regressor": RandomForestRegressor(),
     "Gradient Boosting": GradientBoostingRegressor(),
     "XGBRegressor": XGBRegressor(),
     "CatBoosting Regressor": CatBoostRegressor(verbose=0, iterations = 100),
     "AdaBoost Regressor": AdaBoostRegressor(),
    "ExtraTreesRegressor": ExtraTreesRegressor(),
    "Support Vector Regressor(RBF)": SVR(kernel="rbf"),
    "Support Vector Regressor(linear)": SVR(kernel="linear"),
    "Nu SVR(rbf)": NuSVR(kernel="rbf"),
    "ANN": ANN_model
}
In [61]:
def safe_flatten(y_pred):
    """
    Flattens the array if it's a 2D array with shape (n, 1).
    Useful for ANN predictions.
    """
    if isinstance(y_pred, (np.ndarray, list)) and len(np.shape(y_pred)) == 2 and y_pred.shape[1] == 1:
        return y_pred.flatten()
    return y_pred
In [62]:
r2_train_score = {}
r2_test_score = {}
def evaluate_model(models, X_train, y_train, X_val, y_val):
    for model_name, model in models.items():
        model.fit(X_train, y_train)
        
        y_train_pred = model.predict(X_train)
        y_test_pred = model.predict(X_val)

        y = y_val
        y_pred = safe_flatten(y_test_pred)

        plt.figure(figsize=(8, 6))
        r2 = r2_score(y, y_pred)
        
        sns.scatterplot(x=y, y=y_pred, label='Predicted vs Actual', color='blue')
        sns.regplot(x=y, y=y_pred, scatter=False, label='Regression Line', color='red', ci=None)
        
        plt.xlabel('Actual Values')
        plt.ylabel('Predicted Values')
        plt.title(f'H2 Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model')
        plt.legend()
        plt.grid(True)
        plt.tight_layout()
        plt.savefig(f'H2 Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model.png')
        plt.show()
        
        r2_train_score[model_name] = r2_score(y_train, y_train_pred)
        r2_test_score[model_name] = r2_score(y_val, y_test_pred)
In [63]:
evaluate_model(models, X_train_scaled, y_train.H2, X_val_scaled, y_val.H2)

10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4085 - mae: 1.2107 
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 12ms/step
4/4 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step
In [64]:
score = pd.DataFrame(list(zip(models.keys(), r2_train_score.values(), r2_test_score.values())), columns=["Model","r2_train_score", "r2_test_score"])
score
Out[64]:
Model r2_train_score r2_test_score
0 Linear Regression 0.701773 0.730645
1 Lasso 0.650434 0.684888
2 K-Neighbors Regressor 0.896657 0.911715
3 Decision Tree 0.998124 0.914972
4 Random Forest Regressor 0.983950 0.942061
5 Gradient Boosting 0.966199 0.950161
6 XGBRegressor 0.998037 0.932889
7 CatBoosting Regressor 0.986135 0.951031
8 AdaBoost Regressor 0.856201 0.868602
9 ExtraTreesRegressor 0.998123 0.939666
10 Support Vector Regressor(RBF) 0.568170 0.564914
11 Support Vector Regressor(linear) 0.670485 0.721979
12 Nu SVR(rbf) 0.580037 0.584159
13 ANN 0.975372 0.945724
In [65]:
# Set positions
x = np.arange(len(score['Model']))
width = 0.35  # Width of the bars

# Create plot
fig, ax = plt.subplots(figsize=(16, 8))
bars1 = ax.bar(x - width/2, score['r2_train_score'], width, label='Train R²', color='skyblue')
bars2 = ax.bar(x + width/2, score['r2_test_score'], width, label='Validation R²', color='salmon')

# Add labels and title
ax.set_xlabel('ML Models')
ax.set_ylabel('R² Score')
ax.set_title('H2 Train vs Validation R² Score for Different Models')
ax.set_xticks(x)
ax.set_xticklabels(score['Model'], rotation=45)
ax.legend()

# Add R2 score text on top of bars
for bar in bars1 + bars2:
    yval = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2.0, yval + 0.01, f'{yval:.2f}', ha='center', va='bottom')

plt.tight_layout()
plt.savefig("H2 Train vs Validation R² Score for Different Models")
plt.show()

Predicting CH4 values¶

In [66]:
ANN_model = Sequential([
    Dense(32, input_dim=13),                  # No activation here
    LeakyReLU(alpha=0.1),                    # LeakyReLU activation
    Dense(32, activation='tanh'),            # Tanh for richer non-linearity
    Dense(16, activation='relu'),            # ReLU for simplicity
    Dense(1, activation='linear')            # Linear for regression output
])

# Compile the model
ANN_model.compile(optimizer='adam',
              loss='mean_squared_error',
              metrics=['mae'])


# Train the model
ANN_model.fit(X_train_scaled, y_train.CH4, epochs=500, verbose=1)

# Evaluate the model
loss, mae = ANN_model.evaluate(X_train_scaled, y_train.CH4, verbose=0)
print(f"\nModel evaluation:\nLoss (MSE): {loss:.2f}, MAE: {mae:.2f}")

Epoch 1/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 2s 33ms/step - loss: 70.6160 - mae: 7.6613
Epoch 2/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 67.3477 - mae: 7.4664 
Epoch 3/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 64.4833 - mae: 7.1564 
Epoch 4/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 53.4934 - mae: 6.4522 
Epoch 5/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 42.2167 - mae: 5.4767 
Epoch 6/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 31.6310 - mae: 4.5404 
Epoch 7/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 23.5081 - mae: 3.8119 
Epoch 8/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 16.0438 - mae: 3.1950 
Epoch 9/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.8049 - mae: 2.8408
Epoch 10/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.6834 - mae: 2.8292 
Epoch 11/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 12.3268 - mae: 2.7783 
Epoch 12/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.5295 - mae: 2.5724
Epoch 13/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.8168 - mae: 2.6067 
Epoch 14/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.1576 - mae: 2.5383 
Epoch 15/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.8011 - mae: 2.3645 
Epoch 16/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 10.1528 - mae: 2.4611 
Epoch 17/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.6955 - mae: 2.4197  
Epoch 18/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.7866 - mae: 2.2507 
Epoch 19/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 9.3735 - mae: 2.3614  
Epoch 20/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3820 - mae: 2.2502 
Epoch 21/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.3800 - mae: 2.2129 
Epoch 22/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.9988 - mae: 2.1659 
Epoch 23/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.4071 - mae: 2.1871 
Epoch 24/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.6412 - mae: 2.2654  
Epoch 25/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.0446 - mae: 1.9809 
Epoch 26/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.4494 - mae: 2.0710 
Epoch 27/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 8.0073 - mae: 2.2071 
Epoch 28/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.6046 - mae: 2.1474  
Epoch 29/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.3849 - mae: 1.9433 
Epoch 30/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.7095 - mae: 2.1149  
Epoch 31/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 7.1924 - mae: 2.0663 
Epoch 32/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3011 - mae: 1.7482 
Epoch 33/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.4545 - mae: 1.9535 
Epoch 34/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6591 - mae: 1.8567 
Epoch 35/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 6.1660 - mae: 1.8697 
Epoch 36/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.4235 - mae: 1.7936 
Epoch 37/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3126 - mae: 1.7244 
Epoch 38/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.3850 - mae: 1.7079 
Epoch 39/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.7843 - mae: 1.7979 
Epoch 40/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6026 - mae: 1.8008 
Epoch 41/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2041 - mae: 1.7255 
Epoch 42/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.6470 - mae: 1.7086 
Epoch 43/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.9662 - mae: 1.7107 
Epoch 44/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5097 - mae: 1.6028 
Epoch 45/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.2323 - mae: 1.6789 
Epoch 46/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.8807 - mae: 1.6514 
Epoch 47/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1146 - mae: 1.6787 
Epoch 48/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1518 - mae: 1.5293 
Epoch 49/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 5.1279 - mae: 1.6591 
Epoch 50/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5148 - mae: 1.5401 
Epoch 51/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.8827 - mae: 1.4627 
Epoch 52/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.5812 - mae: 1.5410 
Epoch 53/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.7875 - mae: 1.6548 
Epoch 54/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.0076 - mae: 1.4573 
Epoch 55/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2892 - mae: 1.3714 
Epoch 56/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4445 - mae: 1.5346 
Epoch 57/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.3629 - mae: 1.4796 
Epoch 58/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.1060 - mae: 1.4810 
Epoch 59/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5897 - mae: 1.4172 
Epoch 60/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2000 - mae: 1.4724 
Epoch 61/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.2431 - mae: 1.5309 
Epoch 62/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5536 - mae: 1.4022 
Epoch 63/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3941 - mae: 1.3886 
Epoch 64/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2493 - mae: 1.2816 
Epoch 65/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.7941 - mae: 1.4107 
Epoch 66/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 4.4055 - mae: 1.4253 
Epoch 67/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4501 - mae: 1.3525 
Epoch 68/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8482 - mae: 1.2273 
Epoch 69/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0341 - mae: 1.2827 
Epoch 70/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2336 - mae: 1.2588 
Epoch 71/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9249 - mae: 1.2445 
Epoch 72/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.3735 - mae: 1.2980 
Epoch 73/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4526 - mae: 1.3387 
Epoch 74/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8986 - mae: 1.2358 
Epoch 75/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.5092 - mae: 1.3499 
Epoch 76/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.9582 - mae: 1.3936 
Epoch 77/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2539 - mae: 1.3001 
Epoch 78/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.6417 - mae: 1.3712 
Epoch 79/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.9017 - mae: 1.2169 
Epoch 80/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6269 - mae: 1.1965 
Epoch 81/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0454 - mae: 1.3247 
Epoch 82/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7071 - mae: 1.1964 
Epoch 83/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7534 - mae: 1.2072 
Epoch 84/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.2172 - mae: 1.2585 
Epoch 85/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.8604 - mae: 1.2009 
Epoch 86/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.3693 - mae: 1.1330 
Epoch 87/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.4616 - mae: 1.3586 
Epoch 88/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7562 - mae: 1.1518 
Epoch 89/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6645 - mae: 1.1766 
Epoch 90/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.1838 - mae: 1.0551 
Epoch 91/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6251 - mae: 1.1505 
Epoch 92/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.0481 - mae: 1.0387 
Epoch 93/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 3.0150 - mae: 1.1822 
Epoch 94/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.3989 - mae: 1.0590 
Epoch 95/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.4187 - mae: 1.1082 
Epoch 96/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.4059 - mae: 1.1114 
Epoch 97/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.7873 - mae: 1.1642 
Epoch 98/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.1881 - mae: 1.0860 
Epoch 99/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6421 - mae: 1.1545 
Epoch 100/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.5668 - mae: 1.1148 
Epoch 101/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.3790 - mae: 1.1245 
Epoch 102/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.6308 - mae: 1.1344 
Epoch 103/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9022 - mae: 0.9783 
Epoch 104/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.0725 - mae: 1.0139 
Epoch 105/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.1113 - mae: 1.0321 
Epoch 106/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.2606 - mae: 1.0680 
Epoch 107/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.3831 - mae: 1.0577 
Epoch 108/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8270 - mae: 0.9506 
Epoch 109/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.3821 - mae: 1.0660 
Epoch 110/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8893 - mae: 0.9990 
Epoch 111/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.4212 - mae: 1.0995 
Epoch 112/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.2983 - mae: 1.0525 
Epoch 113/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.7501 - mae: 0.9437 
Epoch 114/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.2655 - mae: 1.0439 
Epoch 115/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8413 - mae: 0.9441 
Epoch 116/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5750 - mae: 0.9140 
Epoch 117/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8818 - mae: 0.9506 
Epoch 118/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9090 - mae: 0.9527 
Epoch 119/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.7036 - mae: 0.9043 
Epoch 120/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8442 - mae: 0.9417 
Epoch 121/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9014 - mae: 0.9426 
Epoch 122/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9455 - mae: 0.9591 
Epoch 123/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9879 - mae: 0.9574 
Epoch 124/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6484 - mae: 0.9014 
Epoch 125/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6820 - mae: 0.9016 
Epoch 126/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9723 - mae: 0.9020 
Epoch 127/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.7140 - mae: 0.9240 
Epoch 128/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9237 - mae: 0.9434 
Epoch 129/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6188 - mae: 0.8930 
Epoch 130/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8393 - mae: 0.9466 
Epoch 131/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.1072 - mae: 0.9716 
Epoch 132/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.1454 - mae: 0.9995 
Epoch 133/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6137 - mae: 0.9135 
Epoch 134/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9466 - mae: 0.9061 
Epoch 135/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9614 - mae: 0.9459 
Epoch 136/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.0597 - mae: 0.9739 
Epoch 137/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.7268 - mae: 0.9127 
Epoch 138/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8693 - mae: 0.9604 
Epoch 139/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5961 - mae: 0.8997 
Epoch 140/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9315 - mae: 0.9334 
Epoch 141/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8167 - mae: 0.9400 
Epoch 142/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5974 - mae: 0.8776 
Epoch 143/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6477 - mae: 0.8815 
Epoch 144/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.8099 - mae: 0.9410 
Epoch 145/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3409 - mae: 0.8179 
Epoch 146/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 2.0140 - mae: 0.9336 
Epoch 147/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5765 - mae: 0.8702 
Epoch 148/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4413 - mae: 0.8122 
Epoch 149/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5498 - mae: 0.8641 
Epoch 150/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6094 - mae: 0.9048 
Epoch 151/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5682 - mae: 0.8713 
Epoch 152/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.7679 - mae: 0.8995 
Epoch 153/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6262 - mae: 0.8826 
Epoch 154/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2974 - mae: 0.7609 
Epoch 155/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3416 - mae: 0.8277 
Epoch 156/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3980 - mae: 0.8240 
Epoch 157/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.7966 - mae: 0.9172 
Epoch 158/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6192 - mae: 0.8875 
Epoch 159/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6593 - mae: 0.8809 
Epoch 160/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4676 - mae: 0.8496 
Epoch 161/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4575 - mae: 0.8376 
Epoch 162/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4609 - mae: 0.8701 
Epoch 163/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4645 - mae: 0.7702 
Epoch 164/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2141 - mae: 0.7704 
Epoch 165/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6663 - mae: 0.8837 
Epoch 166/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3792 - mae: 0.8075 
Epoch 167/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3996 - mae: 0.8480 
Epoch 168/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2760 - mae: 0.8140 
Epoch 169/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.9824 - mae: 0.9692 
Epoch 170/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4997 - mae: 0.8673 
Epoch 171/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5659 - mae: 0.8470 
Epoch 172/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4187 - mae: 0.8239 
Epoch 173/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2377 - mae: 0.7494 
Epoch 174/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6629 - mae: 0.8757 
Epoch 175/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5143 - mae: 0.8550 
Epoch 176/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4326 - mae: 0.8327 
Epoch 177/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5989 - mae: 0.8583 
Epoch 178/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5699 - mae: 0.8404 
Epoch 179/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5473 - mae: 0.8285 
Epoch 180/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3454 - mae: 0.8266 
Epoch 181/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3735 - mae: 0.8323 
Epoch 182/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1374 - mae: 0.7315 
Epoch 183/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3483 - mae: 0.7927 
Epoch 184/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1501 - mae: 0.7668 
Epoch 185/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6541 - mae: 0.8575 
Epoch 186/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5430 - mae: 0.8465 
Epoch 187/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5626 - mae: 0.8491 
Epoch 188/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4042 - mae: 0.8058 
Epoch 189/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.6736 - mae: 0.8591 
Epoch 190/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2800 - mae: 0.7956 
Epoch 191/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4494 - mae: 0.8154 
Epoch 192/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2680 - mae: 0.7744 
Epoch 193/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4634 - mae: 0.7994 
Epoch 194/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2423 - mae: 0.7584 
Epoch 195/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5262 - mae: 0.8349 
Epoch 196/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3783 - mae: 0.8160 
Epoch 197/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3314 - mae: 0.7922 
Epoch 198/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5603 - mae: 0.8174 
Epoch 199/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3356 - mae: 0.7514 
Epoch 200/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2577 - mae: 0.7678 
Epoch 201/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3354 - mae: 0.8149 
Epoch 202/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3238 - mae: 0.7848 
Epoch 203/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3904 - mae: 0.8046 
Epoch 204/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0952 - mae: 0.7654 
Epoch 205/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1305 - mae: 0.7352 
Epoch 206/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1891 - mae: 0.7615 
Epoch 207/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4054 - mae: 0.8069 
Epoch 208/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2488 - mae: 0.7582 
Epoch 209/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4230 - mae: 0.8258 
Epoch 210/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2159 - mae: 0.7742 
Epoch 211/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1850 - mae: 0.7596 
Epoch 212/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1784 - mae: 0.7351 
Epoch 213/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0477 - mae: 0.7052 
Epoch 214/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5931 - mae: 0.8128 
Epoch 215/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2815 - mae: 0.7677 
Epoch 216/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2788 - mae: 0.7630 
Epoch 217/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9537 - mae: 0.6925 
Epoch 218/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0886 - mae: 0.7243 
Epoch 219/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3045 - mae: 0.7542 
Epoch 220/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0693 - mae: 0.7230 
Epoch 221/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5097 - mae: 0.8097 
Epoch 222/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1612 - mae: 0.7460 
Epoch 223/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9942 - mae: 0.6677 
Epoch 224/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1223 - mae: 0.7157 
Epoch 225/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1008 - mae: 0.7213 
Epoch 226/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4091 - mae: 0.7587 
Epoch 227/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0882 - mae: 0.7121 
Epoch 228/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9510 - mae: 0.6831 
Epoch 229/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2222 - mae: 0.7332 
Epoch 230/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4082 - mae: 0.7727 
Epoch 231/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3565 - mae: 0.7392 
Epoch 232/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9561 - mae: 0.6831 
Epoch 233/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2139 - mae: 0.7154 
Epoch 234/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0600 - mae: 0.7202 
Epoch 235/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0548 - mae: 0.6985 
Epoch 236/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1280 - mae: 0.7217 
Epoch 237/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1638 - mae: 0.7333 
Epoch 238/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9602 - mae: 0.6779 
Epoch 239/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1121 - mae: 0.7170 
Epoch 240/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1837 - mae: 0.7256 
Epoch 241/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0395 - mae: 0.7047 
Epoch 242/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2669 - mae: 0.7388 
Epoch 243/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1946 - mae: 0.7203 
Epoch 244/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1240 - mae: 0.7401 
Epoch 245/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1183 - mae: 0.7217 
Epoch 246/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2161 - mae: 0.7351 
Epoch 247/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1895 - mae: 0.7459 
Epoch 248/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3629 - mae: 0.7579 
Epoch 249/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0308 - mae: 0.6975 
Epoch 250/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2433 - mae: 0.7711 
Epoch 251/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0634 - mae: 0.6841 
Epoch 252/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1000 - mae: 0.7133 
Epoch 253/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3446 - mae: 0.7421 
Epoch 254/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2156 - mae: 0.7310 
Epoch 255/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0830 - mae: 0.7280 
Epoch 256/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2456 - mae: 0.7582 
Epoch 257/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9643 - mae: 0.6617 
Epoch 258/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3321 - mae: 0.7617 
Epoch 259/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2529 - mae: 0.7236 
Epoch 260/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9092 - mae: 0.6477 
Epoch 261/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1769 - mae: 0.7254 
Epoch 262/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3940 - mae: 0.7260 
Epoch 263/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2523 - mae: 0.7200 
Epoch 264/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3162 - mae: 0.7442 
Epoch 265/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2829 - mae: 0.7513 
Epoch 266/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0449 - mae: 0.7030 
Epoch 267/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9424 - mae: 0.6881 
Epoch 268/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3093 - mae: 0.7178 
Epoch 269/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0206 - mae: 0.6624 
Epoch 270/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9399 - mae: 0.6543 
Epoch 271/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3514 - mae: 0.7346 
Epoch 272/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2914 - mae: 0.7249 
Epoch 273/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1557 - mae: 0.7589 
Epoch 274/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2652 - mae: 0.7585 
Epoch 275/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0496 - mae: 0.6791 
Epoch 276/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4373 - mae: 0.7408 
Epoch 277/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1234 - mae: 0.7037 
Epoch 278/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0827 - mae: 0.7222 
Epoch 279/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0610 - mae: 0.7003 
Epoch 280/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9371 - mae: 0.6900 
Epoch 281/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0118 - mae: 0.6881 
Epoch 282/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9556 - mae: 0.6381 
Epoch 283/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1929 - mae: 0.7074 
Epoch 284/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0423 - mae: 0.7081 
Epoch 285/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9400 - mae: 0.6582 
Epoch 286/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0895 - mae: 0.6892 
Epoch 287/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0601 - mae: 0.6677 
Epoch 288/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0374 - mae: 0.6920 
Epoch 289/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9185 - mae: 0.6640 
Epoch 290/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9431 - mae: 0.6692 
Epoch 291/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9391 - mae: 0.6216 
Epoch 292/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9167 - mae: 0.6531 
Epoch 293/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0084 - mae: 0.6657 
Epoch 294/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0180 - mae: 0.6322 
Epoch 295/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8524 - mae: 0.6094 
Epoch 296/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9020 - mae: 0.6025 
Epoch 297/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1155 - mae: 0.7014 
Epoch 298/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0438 - mae: 0.6529 
Epoch 299/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9610 - mae: 0.6119 
Epoch 300/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2405 - mae: 0.7017 
Epoch 301/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8934 - mae: 0.6289 
Epoch 302/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0901 - mae: 0.6500 
Epoch 303/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0268 - mae: 0.6503 
Epoch 304/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0612 - mae: 0.6857 
Epoch 305/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0559 - mae: 0.6749 
Epoch 306/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8302 - mae: 0.6018 
Epoch 307/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8969 - mae: 0.6315 
Epoch 308/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3418 - mae: 0.6979 
Epoch 309/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3480 - mae: 0.7236 
Epoch 310/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9808 - mae: 0.7189 
Epoch 311/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4512 - mae: 0.7422 
Epoch 312/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9400 - mae: 0.6373 
Epoch 313/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7427 - mae: 0.5689 
Epoch 314/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9100 - mae: 0.6423 
Epoch 315/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9477 - mae: 0.6236 
Epoch 316/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9293 - mae: 0.6710 
Epoch 317/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0562 - mae: 0.6867 
Epoch 318/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8793 - mae: 0.6276 
Epoch 319/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8735 - mae: 0.6431 
Epoch 320/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9449 - mae: 0.6421 
Epoch 321/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1383 - mae: 0.6810 
Epoch 322/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7286 - mae: 0.5520 
Epoch 323/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1844 - mae: 0.6646 
Epoch 324/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8820 - mae: 0.6155 
Epoch 325/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0783 - mae: 0.7087 
Epoch 326/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9130 - mae: 0.6459 
Epoch 327/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0431 - mae: 0.6538 
Epoch 328/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9947 - mae: 0.6803 
Epoch 329/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9793 - mae: 0.6437 
Epoch 330/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8686 - mae: 0.6176 
Epoch 331/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8304 - mae: 0.5991 
Epoch 332/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0270 - mae: 0.6865 
Epoch 333/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0400 - mae: 0.6838 
Epoch 334/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3456 - mae: 0.7638 
Epoch 335/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9271 - mae: 0.6914 
Epoch 336/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1495 - mae: 0.7154 
Epoch 337/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.4542 - mae: 0.7570 
Epoch 338/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1514 - mae: 0.6707 
Epoch 339/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9134 - mae: 0.6118 
Epoch 340/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3325 - mae: 0.7508 
Epoch 341/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9095 - mae: 0.6332 
Epoch 342/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9739 - mae: 0.6055 
Epoch 343/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7662 - mae: 0.6054 
Epoch 344/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2827 - mae: 0.7390 
Epoch 345/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2914 - mae: 0.7563 
Epoch 346/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.2493 - mae: 0.7758 
Epoch 347/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0907 - mae: 0.7114 
Epoch 348/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.3786 - mae: 0.7123 
Epoch 349/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8551 - mae: 0.6055 
Epoch 350/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1469 - mae: 0.6521 
Epoch 351/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7097 - mae: 0.5409 
Epoch 352/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8808 - mae: 0.6047 
Epoch 353/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9680 - mae: 0.6306 
Epoch 354/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7024 - mae: 0.5464 
Epoch 355/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9843 - mae: 0.6309 
Epoch 356/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7761 - mae: 0.5934 
Epoch 357/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9253 - mae: 0.6418 
Epoch 358/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.5671 - mae: 0.8066 
Epoch 359/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0630 - mae: 0.6956 
Epoch 360/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0088 - mae: 0.6227 
Epoch 361/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8778 - mae: 0.6120 
Epoch 362/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9498 - mae: 0.6263 
Epoch 363/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7678 - mae: 0.6044 
Epoch 364/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9597 - mae: 0.6340 
Epoch 365/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0817 - mae: 0.6192 
Epoch 366/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8348 - mae: 0.5877 
Epoch 367/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7662 - mae: 0.5881 
Epoch 368/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9664 - mae: 0.5928 
Epoch 369/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9573 - mae: 0.6290 
Epoch 370/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6304 - mae: 0.5278 
Epoch 371/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8430 - mae: 0.5789 
Epoch 372/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8640 - mae: 0.5843 
Epoch 373/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9841 - mae: 0.6142 
Epoch 374/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9159 - mae: 0.6012 
Epoch 375/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9002 - mae: 0.5914 
Epoch 376/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8551 - mae: 0.6036 
Epoch 377/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8661 - mae: 0.6111 
Epoch 378/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9698 - mae: 0.6380 
Epoch 379/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9427 - mae: 0.6315 
Epoch 380/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8365 - mae: 0.5955 
Epoch 381/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9933 - mae: 0.6244 
Epoch 382/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9553 - mae: 0.6306 
Epoch 383/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7316 - mae: 0.5657 
Epoch 384/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8707 - mae: 0.6479 
Epoch 385/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9535 - mae: 0.6645 
Epoch 386/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9664 - mae: 0.6005 
Epoch 387/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9679 - mae: 0.6214 
Epoch 388/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7908 - mae: 0.5946 
Epoch 389/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9552 - mae: 0.6455 
Epoch 390/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7900 - mae: 0.5956 
Epoch 391/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0715 - mae: 0.6283 
Epoch 392/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8858 - mae: 0.6079 
Epoch 393/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7583 - mae: 0.5670 
Epoch 394/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8169 - mae: 0.5899 
Epoch 395/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7155 - mae: 0.5847 
Epoch 396/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8196 - mae: 0.5901 
Epoch 397/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0240 - mae: 0.6588 
Epoch 398/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9131 - mae: 0.6484 
Epoch 399/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9884 - mae: 0.6736 
Epoch 400/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8741 - mae: 0.5910 
Epoch 401/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9638 - mae: 0.6140 
Epoch 402/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8647 - mae: 0.5982 
Epoch 403/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8738 - mae: 0.6082 
Epoch 404/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7383 - mae: 0.5566 
Epoch 405/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9866 - mae: 0.6301 
Epoch 406/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7982 - mae: 0.5523 
Epoch 407/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7243 - mae: 0.5301 
Epoch 408/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8406 - mae: 0.5778 
Epoch 409/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9663 - mae: 0.5669 
Epoch 410/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7309 - mae: 0.5620 
Epoch 411/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9836 - mae: 0.5986 
Epoch 412/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6865 - mae: 0.5378 
Epoch 413/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8375 - mae: 0.5795 
Epoch 414/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8379 - mae: 0.5352 
Epoch 415/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8321 - mae: 0.5724 
Epoch 416/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6896 - mae: 0.5526 
Epoch 417/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8542 - mae: 0.6395 
Epoch 418/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1877 - mae: 0.6802 
Epoch 419/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0857 - mae: 0.6420 
Epoch 420/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8049 - mae: 0.5627 
Epoch 421/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7135 - mae: 0.5287 
Epoch 422/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7744 - mae: 0.5833 
Epoch 423/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7775 - mae: 0.5693 
Epoch 424/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7600 - mae: 0.5784 
Epoch 425/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9504 - mae: 0.5906 
Epoch 426/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8685 - mae: 0.5775 
Epoch 427/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8219 - mae: 0.5566 
Epoch 428/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7985 - mae: 0.5378 
Epoch 429/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7892 - mae: 0.5556 
Epoch 430/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7033 - mae: 0.5366 
Epoch 431/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8739 - mae: 0.5788 
Epoch 432/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7354 - mae: 0.5097 
Epoch 433/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7075 - mae: 0.5305 
Epoch 434/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7664 - mae: 0.5638 
Epoch 435/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7571 - mae: 0.5417 
Epoch 436/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7440 - mae: 0.5285 
Epoch 437/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0028 - mae: 0.5797 
Epoch 438/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6854 - mae: 0.5285 
Epoch 439/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0163 - mae: 0.6007 
Epoch 440/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9600 - mae: 0.5539 
Epoch 441/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0031 - mae: 0.6130 
Epoch 442/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9660 - mae: 0.5758 
Epoch 443/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9638 - mae: 0.5868 
Epoch 444/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8775 - mae: 0.5990 
Epoch 445/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8684 - mae: 0.5577 
Epoch 446/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9240 - mae: 0.5830 
Epoch 447/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0143 - mae: 0.6310 
Epoch 448/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0097 - mae: 0.6363 
Epoch 449/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8631 - mae: 0.6690 
Epoch 450/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7302 - mae: 0.5755 
Epoch 451/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8937 - mae: 0.6261 
Epoch 452/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.1362 - mae: 0.6669 
Epoch 453/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7067 - mae: 0.5592 
Epoch 454/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7850 - mae: 0.5588 
Epoch 455/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6798 - mae: 0.5574 
Epoch 456/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0039 - mae: 0.6136 
Epoch 457/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6463 - mae: 0.5145 
Epoch 458/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8742 - mae: 0.5631 
Epoch 459/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8664 - mae: 0.5443 
Epoch 460/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8504 - mae: 0.5641 
Epoch 461/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7152 - mae: 0.5247 
Epoch 462/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7752 - mae: 0.5572 
Epoch 463/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9584 - mae: 0.6286 
Epoch 464/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8388 - mae: 0.6013 
Epoch 465/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7425 - mae: 0.5554 
Epoch 466/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8407 - mae: 0.5942 
Epoch 467/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9818 - mae: 0.6339 
Epoch 468/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8249 - mae: 0.5704 
Epoch 469/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8735 - mae: 0.5803 
Epoch 470/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8964 - mae: 0.6094 
Epoch 471/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8151 - mae: 0.5787 
Epoch 472/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9678 - mae: 0.6135 
Epoch 473/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7901 - mae: 0.5616 
Epoch 474/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6552 - mae: 0.4934 
Epoch 475/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7844 - mae: 0.5473 
Epoch 476/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7156 - mae: 0.5509 
Epoch 477/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8273 - mae: 0.5840 
Epoch 478/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9484 - mae: 0.5992 
Epoch 479/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8047 - mae: 0.5694 
Epoch 480/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7201 - mae: 0.5543 
Epoch 481/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7042 - mae: 0.5518 
Epoch 482/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8715 - mae: 0.5846 
Epoch 483/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8387 - mae: 0.5530 
Epoch 484/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6872 - mae: 0.5267 
Epoch 485/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8135 - mae: 0.5773 
Epoch 486/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8834 - mae: 0.5813 
Epoch 487/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7122 - mae: 0.5464 
Epoch 488/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.5971 - mae: 0.4974 
Epoch 489/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7398 - mae: 0.5271 
Epoch 490/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8097 - mae: 0.5532 
Epoch 491/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.5899 - mae: 0.5076 
Epoch 492/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7646 - mae: 0.5289 
Epoch 493/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.9578 - mae: 0.5835 
Epoch 494/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6186 - mae: 0.5065 
Epoch 495/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.6257 - mae: 0.5189 
Epoch 496/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8987 - mae: 0.5490 
Epoch 497/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.5790 - mae: 0.4977 
Epoch 498/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8591 - mae: 0.5642 
Epoch 499/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.8338 - mae: 0.5641 
Epoch 500/500
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 1.0352 - mae: 0.5944 

Model evaluation:
Loss (MSE): 0.74, MAE: 0.53
In [67]:
models = {
    "Linear Regression": LinearRegression(),
    "Lasso": Lasso(),
    "K-Neighbors Regressor": KNeighborsRegressor(),
    "Decision Tree": DecisionTreeRegressor(),
     "Random Forest Regressor": RandomForestRegressor(),
     "Gradient Boosting": GradientBoostingRegressor(),
     "XGBRegressor": XGBRegressor(),
     "CatBoosting Regressor": CatBoostRegressor(verbose=0, iterations = 100),
     "AdaBoost Regressor": AdaBoostRegressor(),
    "ExtraTreesRegressor": ExtraTreesRegressor(),
    "Support Vector Regressor(RBF)": SVR(kernel="rbf"),
    "Support Vector Regressor(linear)": SVR(kernel="linear"),
    "Nu SVR(rbf)": NuSVR(kernel="rbf"),
    "ANN": ANN_model
}
In [68]:
def safe_flatten(y_pred):
    """
    Flattens the array if it's a 2D array with shape (n, 1).
    Useful for ANN predictions.
    """
    if isinstance(y_pred, (np.ndarray, list)) and len(np.shape(y_pred)) == 2 and y_pred.shape[1] == 1:
        return y_pred.flatten()
    return y_pred
In [69]:
r2_train_score = {}
r2_test_score = {}
def evaluate_model(models, X_train, y_train, X_val, y_val):
    for model_name, model in models.items():
        model.fit(X_train, y_train)
        
        y_train_pred = model.predict(X_train)
        y_test_pred = model.predict(X_val)

        y = y_val
        y_pred = safe_flatten(y_test_pred)

        plt.figure(figsize=(8, 6))
        r2 = r2_score(y, y_pred)
        
        sns.scatterplot(x=y, y=y_pred, label='Predicted vs Actual', color='blue')
        sns.regplot(x=y, y=y_pred, scatter=False, label='Regression Line', color='red', ci=None)
        
        plt.xlabel('Actual Values')
        plt.ylabel('Predicted Values')
        plt.title(f'CH4 Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model')
        plt.legend()
        plt.grid(True)
        plt.tight_layout()
        plt.savefig(f'CH4 Actual vs Predicted Values (R² Score: {r2:.4f}) for {model_name} model.png')
        plt.show()
        
        r2_train_score[model_name] = r2_score(y_train, y_train_pred)
        r2_test_score[model_name] = r2_score(y_val, y_test_pred)
In [70]:
evaluate_model(models, X_train_scaled, y_train.CH4, X_val_scaled, y_val.CH4)

10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.7597 - mae: 0.5493 
10/10 ━━━━━━━━━━━━━━━━━━━━ 0s 12ms/step
4/4 ━━━━━━━━━━━━━━━━━━━━ 0s 19ms/step
In [71]:
score = pd.DataFrame(list(zip(models.keys(), r2_train_score.values(), r2_test_score.values())), columns=["Model","r2_train_score", "r2_test_score"])
score
Out[71]:
Model r2_train_score r2_test_score
0 Linear Regression 0.257236 0.273732
1 Lasso 0.000000 -0.033079
2 K-Neighbors Regressor 0.746015 0.721042
3 Decision Tree 0.995971 0.452798
4 Random Forest Regressor 0.950031 0.796166
5 Gradient Boosting 0.915502 0.760806
6 XGBRegressor 0.995611 0.790316
7 CatBoosting Regressor 0.959128 0.821011
8 AdaBoost Regressor 0.708777 0.549022
9 ExtraTreesRegressor 0.995971 0.832564
10 Support Vector Regressor(RBF) 0.518792 0.533648
11 Support Vector Regressor(linear) 0.213773 0.195725
12 Nu SVR(rbf) 0.491429 0.525306
13 ANN 0.938276 0.762182
In [72]:
# Set positions
x = np.arange(len(score['Model']))
width = 0.35  # Width of the bars

# Create plot
fig, ax = plt.subplots(figsize=(16, 8))
bars1 = ax.bar(x - width/2, score['r2_train_score'], width, label='Train R²', color='skyblue')
bars2 = ax.bar(x + width/2, score['r2_test_score'], width, label='Validation R²', color='salmon')

# Add labels and title
ax.set_xlabel('ML Models')
ax.set_ylabel('R² Score')
ax.set_title('CH4 Train vs Validation R² Score for Different Models')
ax.set_xticks(x)
ax.set_xticklabels(score['Model'], rotation=45)
ax.legend()

# Add R2 score text on top of bars
for bar in bars1 + bars2:
    yval = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2.0, yval + 0.01, f'{yval:.2f}', ha='center', va='bottom')

plt.tight_layout()
plt.savefig("CH4 Train vs Validation R² Score for Different Models")
plt.show()
In [73]:
import zipfile
import os

with zipfile.ZipFile('kaggle_output.zip', 'w') as zipf:
    for file in os.listdir():
        if file.endswith(('.png')):
            zipf.write(file)
In [ ]: